Author name cluster

Zidong Du

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

30 papers

2 author rows

AAAI Conference 2026 Conference Paper

Efficient Diffusion Planning with Temporal Diffusion

Jiaming Guo
Rui Zhang
Zerun Li
Yunkai Gao
Shaohui Peng
Siming Lan
Xing Hu
Zidong Du

Diffusion planning is a promising method for learning high-performance policies from offline data. To avoid the impact of discrepancies between planning and reality on performance, previous works generate new plans at each time step. However, this incurs significant computational overhead and leads to lower decision frequencies, and frequent plan switching may also affect performance. In contrast, humans might create detailed short-term plans and more general, sometimes vague, long-term plans, and adjust them over time. Inspired by this, we propose the Temporal Diffusion Planner (TDP) which improves decision efficiency by distributing the denoising steps across the time dimension. TDP begins by generating an initial plan that becomes progressively more vague over time. At each subsequent time step, rather than generating an entirely new plan, TDP updates the previous one with a small number of denoising steps. This reduces the average number of denoising steps, improving decision efficiency. Additionally, we introduce an automated replanning mechanism to prevent significant deviations between the plan and reality. Experiments on D4RL show that, compared to previous works that generate new plans every time step, TDP significantly improves the decision-making frequency by 11-24.8 times while achieving higher or comparable performance.

PDF Details DOI

AAAI Conference 2026 Conference Paper

QiMeng-CRUX: Narrowing the Gap Between Natural Language and Verilog via Core Refined Understanding eXpression

Lei Huang
Rui Zhang
Jiaming Guo
Yang Zhang
Di Huang
Shuyao Cheng
Pengwei Jin
Chongxiao Li

Large language models (LLMs) have shown promising capabilities in hardware description language (HDL) generation. However, existing approaches often rely on free-form natural language descriptions that are often ambiguous, redundant, and unstructured, which poses significant challenges for downstream Verilog code generation. We treat hardware code generation as a complex transformation from an open-ended natural language space to a domain-specific, highly constrained target space. To bridge this gap, we introduce Core Refined Understanding eXpression (CRUX), a structured intermediate space that captures the essential semantics of user intent while organizing the expression for precise Verilog code generation. We further design a two-stage training framework, comprising Joint Expression Modeling and Dual-Space Optimization, to enhance the quality of both CRUX and Verilog code. Experiments across multiple Verilog generation benchmarks demonstrate that our model, QiMeng-CRUX, achieves state-of-the-art performance among general models, particularly under challenging design tasks. Furthermore, the CRUX space proves transferable and beneficial when used as input prompts for other code models, highlighting its effectiveness in narrowing the gap between free-form natural language descriptions and precise Verilog generation.

PDF Details DOI

AAAI Conference 2026 Conference Paper

StepFun-Formalizer: Unlocking the Autoformalization Potential of LLMs Through Knowledge-Reasoning Fusion

Yutong Wu
Di Huang
Ruosi Wan
Yue Peng
Shijie Shang
Chenrui Cao
Lei Qi
Rui Zhang

Autoformalization aims to translate natural-language mathematical statements into a formal language. While LLMs have accelerated progress in this area, existing methods still suffer from low accuracy. We identify two key abilities for effective autoformalization: comprehensive mastery of formal-language domain knowledge, and reasoning capability of natural language problem understanding and informal-formal alignment. Without the former, a model cannot identify the correct formal objects; without the latter, it struggles to interpret real-world contexts and map them precisely into formal expressions. To address these gaps, we introduce ThinkingF, a data synthesis and training pipeline that improves both abilities. First, we construct two datasets: one by distilling and selecting large-scale examples rich in formal knowledge, and another by generating informal-to-formal reasoning trajectories guided by expert-designed templates. We then apply SFT and RLVR with these datasets to further fuse and refine the two abilities. The resulting 7B and 32B models exhibit both comprehensive formal knowledge and strong informal-to-formal reasoning. Notably, StepFun-Formalizer-32B achieves SOTA BEq@1 scores of 40.5% on FormalMATH-Lite and 26.7% on ProverBench, surpassing all prior general-purpose and specialized models.

PDF Details DOI

IJCAI Conference 2025 Conference Paper

Automated Superscalar Processor Design by Learning Data Dependencies

Shuyao Cheng
Rui Zhang
Wenkai He
Pengwei Jin
Chongxiao Li
Zidong Du
Xing Hu
Yifan Hao

Automated processor design, which can significantly reduce human efforts and accelerate design cycles, has received considerable attention. While recent advancements have automatically designed single-cycle processors that execute one instruction per cycle, their performance cannot compete with modern superscalar processors that execute multiple instructions per cycle. Previous methods fail on superscalar processor design because they cannot address inter-instruction data dependencies, leading to inefficient sequential instruction execution. This paper proposes a novel approach to automatically designing superscalar processors using a hardware-friendly model called the Stateful Binary Speculation Diagram (State-BSD). We observe that processor parallelism can be enhanced through on-the-fly inter-instruction dependent data predictors, reusing the processor's internal states to learn the data dependency. To meet the challenge of both hardware-resource limitation and design functional correctness, State-BSD consists of two components: 1) a lightweight state-selector trained by simulated annealing method to detect the most reusable processor states and store them in a small buffer; and 2) a highly precise state-speculator trained by BSD expansion method to predict the inter-instruction dependent data using the selected states. It is the first work to achieve the automated superscalar processor design, i. e. QiMeng-CPU-v2, which improves the performance by about 380x than the state-of-the-art automated design and is comparable to human-designed superscalar processors such as ARM Cortex A53.

PDF Details DOI

AAAI Conference 2025 Conference Paper

InverseCoder: Self-improving Instruction-Tuned Code LLMs with Inverse-Instruct

Yutong Wu
Di Huang
Wenxuan Shi
Wei Wang
Yewen Pu
Lingzhe Gao
Shihao Liu
Ziyuan Nan

Recent advancements in open-source code large language models (LLMs) have been driven by fine-tuning on the data generated from powerful closed-source LLMs, which are expensive to obtain. This paper explores whether it is possible to use a fine-tuned open-source model to generate additional data to augment its instruction-tuning dataset. We make two observations: (1) A code snippet can serve as the response to different instructions. (2) Instruction-tuned code LLMs perform better at translating code into instructions than the reverse. Based on these observations, we propose Inverse-Instruct, a data augmentation technique that uses a fine-tuned LLM to generate additional instructions of code responses from its own training dataset. The additional instruction-response pairs are added to the original dataset, and a stronger code LLM can be obtained by fine-tuning on the augmented dataset. We empirically validate Inverse-Instruct on a range of open-source code models (e.g. CodeLlama-Python and DeepSeek-Coder) and benchmarks (e.g., HumanEval(+), MBPP(+), DS-1000 and MultiPL-E), showing it consistently improves the base models.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

QiMeng-CodeV-R1: Reasoning-Enhanced Verilog Generation

Yaoyu Zhu
Di Huang
Hanqi Lyu
Xiaoyun Zhang
Chongxiao Li
Wenxuan Shi
Yutong Wu
Jianan Mu

Large language models (LLMs) trained via reinforcement learning with verifiable reward (RLVR) have achieved breakthroughs on tasks with explicit, automatable verification, such as software programming and mathematical problems. Extending RLVR to electronic design automation (EDA), especially automatically generating hardware description languages (HDLs) like Verilog from natural-language (NL) specifications, however, poses three key challenges: the lack of automated and accurate verification environments, the scarcity of high-quality NL-code pairs, and the prohibitive computation cost of RLVR. To this end, we introduce CodeV-R1, an RLVR framework for training Verilog generation LLMs. First, we develop a rule-based testbench generator that performs robust equivalence checking against golden references. Second, we propose a round-trip data synthesis method that pairs open-source Verilog snippets with LLM-generated NL descriptions, verifies code–NL–code consistency via the generated testbench, and filters out inequivalent examples to yield a high-quality dataset. Third, we employ a two-stage "distill-then-RL" training pipeline: distillation for the cold start of reasoning abilities, followed by adaptive DAPO, our novel RLVR algorithm that can reduce training cost by adaptively adjusting sampling rate. The resulting model, CodeV-R1-7B, achieves 68. 6 \% and 72. 9 \% pass@1 on VerilogEval v2 and RTLLM v1. 1, respectively, surpassing prior state-of-the-art by 12$\sim$20 \%, while even exceeding the performance of 671B DeepSeek-R1 on RTLLM. We have released our model, training code, and dataset to facilitate research in EDA and LLM communities.

PDF Details

NeurIPS Conference 2025 Conference Paper

QiMeng-SALV: Signal-Aware Learning for Verilog Code Generation

Yang Zhang
Rui Zhang
Jiaming Guo
Huang Lei
Di Huang
Yunpu Zhao
Shuyao Cheng
Pengwei Jin

The remarkable progress of Large Language Models (LLMs) presents promising opportunities for Verilog code generation which is significantly important for automated circuit design. The lacking of meaningful functional rewards hinders the preference optimization based on Reinforcement Learning (RL) for producing functionally correct Verilog code. In this paper, we propose Signal-Aware Learning for Verilog code generation (QiMeng-SALV) by leveraging code segments of functionally correct output signal to optimize RL training. Considering Verilog code specifies the structural interconnection of hardware gates and wires so that different output signals are independent, the key insight of QiMeng-SALV is to extract verified signal-aware implementations in partially incorrect modules, so as to enhance the extraction of meaningful functional rewards. Roughly, we verify the functional correctness of signals in generated module by comparing with that of reference module in the training data. Then abstract syntax tree (AST) is employed to identify signal-aware code segments which can provide meaningful functional rewards from erroneous modules. Finally, we introduce signal-aware DPO which is optimized on the correct signal-level code segments, thereby preventing noise and interference from incorrect signals. The proposed QiMeng-SALV underscores the paradigm shift from conventional module-level to fine-grained signal-level optimization in Verilog code generation, addressing the issue of insufficient functional rewards. Experiments demonstrate that our method achieves state-of-the-art performance on VerilogEval and RTLLM, with a 7B parameter model matching the performance of the DeepSeek v3 671B model and significantly outperforming the leading open-source model CodeV trained on the same dataset.

PDF Details

IJCAI Conference 2024 Conference Paper

Automated CPU Design by Learning from Input-Output Examples

Shuyao Cheng
Pengwei Jin
Qi Guo
Zidong Du
Rui Zhang
Xing Hu
Yongwei Zhao
Yifan Hao

Designing a central processing unit (CPU) requires intensive manual work of talented experts to implement the circuit logic from design specifications. Although considerable progress has been made in electronic design automation (EDA) to relieve human efforts, all existing EDA tools require hand-crafted formal program codes (e. g. , Verilog, Chisel, or C) as the input. To automate the CPU design without human programming, we are motivated to learn the CPU design from only input-output (IO) examples. The key challenge is that the learned CPU design should have almost zero tolerance for inaccuracy, which makes well-known approximate algorithms such as neural networks ineffective. We propose a new AI approach to generate the CPU design in the form of a large-scale Boolean function, from only external IO examples instead of formal program code. This approach employs a novel graph structure called Binary Speculative Diagram (BSD) to approximate the CPU-scale Boolean function accurately. We propose an efficient BSD expansion method based on Boolean Distance, a new metric to quantitatively measure the structural similarity between Boolean functions, gradually increasing the design accuracy up to 100%. Our approach generates an industrial-scale RISC-V CPU design within 5 hours, reducing the design cycle by about 1000x without human involvement. The taped-out chip, Enlightenment-1, the world's first CPU designed by AI, successfully runs the Linux operating system and performs comparably against the human-design Intel 80486SX CPU. Our approach even autonomously discovers human knowledge of the von Neumann architecture.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Emergent Communication for Numerical Concepts Generalization

Enshuai Zhou
Yifan Hao
Rui Zhang
Yuxuan Guo
Zidong Du
Xishan Zhang
Xinkai Song
Chao Wang

Research on emergent communication has recently gained significant traction as a promising avenue for the linguistic community to unravel human language's origins and explore artificial intelligence's generalization capabilities. Current research has predominantly concentrated on recognizing qualitative patterns of object attributes(e.g., shape and color) and paid little attention to the quantitative relationship among object quantities which is known as the part of numerical concepts. The ability to generalize numerical concepts, i.e., counting and calculations with unseen quantities, is essential, as it mirrors humans' foundational abstract reasoning abilities. In this work, we introduce the NumGame, leveraging the referential game framework, forcing agents to communicate and generalize the numerical concepts effectively. Inspired by the human learning process of numbers, we present a two-stage training approach that sequentially fosters a rudimentary numerical sense followed by the ability of arithmetic calculation, ultimately aiding agents in generating semantically stable and unambiguous language for numerical concepts. The experimental results indicate the impressive generalization capabilities to unseen quantities and regularity of the language emergence from communication.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Hypothesis, Verification, and Induction: Grounding Large Language Models with Self-Driven Skill Learning

Shaohui Peng
Xing Hu
Qi Yi
Rui Zhang
Jiaming Guo
Di Huang
Zikang Tian
Ruizhi Chen

Large language models (LLMs) show their powerful automatic reasoning and planning capability with a wealth of semantic knowledge about the human world. However, the grounding problem still hinders the applications of LLMs in the real-world environment. Existing studies try to fine-tune the LLM or utilize pre-defined behavior APIs to bridge the LLMs and the environment, which not only costs huge human efforts to customize for every single task but also weakens the generality strengths of LLMs. To autonomously ground the LLM onto the environment, we proposed the Hypothesis, Verification, and Induction (HYVIN) framework to automatically and progressively ground the LLM with self-driven skill learning. HYVIN first employs the LLM to propose the hypothesis of sub-goals to achieve tasks and then verify the feasibility of the hypothesis via interacting with the underlying environment. Once verified, HYVIN can then learn generalized skills with the guidance of these successfully grounded subgoals. These skills can be further utilized to accomplish more complex tasks that fail to pass the verification phase. Verified in the famous instruction following task set, BabyAI, HYVIN achieves comparable performance in the most challenging tasks compared with imitation learning methods that cost millions of demonstrations, proving the effectiveness of learned skills and showing the feasibility and efficiency of our framework.

PDF Details DOI

ICML Conference 2024 Conference Paper

Prompt-based Visual Alignment for Zero-shot Policy Transfer

Haihan Gao
Rui Zhang 0040
Qi Yi
Hantao Yao
Haochen Li 0002
Jiaming Guo
Shaohui Peng
Yunkai Gao 0001

Overfitting in RL has become one of the main obstacles to applications in reinforcement learning(RL). Existing methods do not provide explicit semantic constrain for the feature extractor, hindering the agent from learning a unified cross-domain representation and resulting in performance degradation on unseen domains. Besides, abundant data from multiple domains are needed. To address these issues, in this work, we propose prompt-based visual alignment (PVA), a robust framework to mitigate the detrimental domain bias in the image for zero-shot policy transfer. Inspired that Visual-Language Model (VLM) can serve as a bridge to connect both text space and image space, we leverage the semantic information contained in a text sequence as an explicit constraint to train a visual aligner. Thus, the visual aligner can map images from multiple domains to a unified domain and achieve good generalization performance. To better depict semantic information, prompt tuning is applied to learn a sequence of learnable tokens. With explicit constraints of semantic information, PVA can learn unified cross-domain representation under limited access to cross-domain data and achieves great zero-shot generalization ability in unseen domains. We verify PVA on a vision-based autonomous driving task with CARLA simulator. Experiments show that the agent generalizes well on unseen domains under limited access to multi-domain data.

Details

NeurIPS Conference 2023 Conference Paper

ANPL: Towards Natural Programming with Interactive Decomposition

Di Huang
Ziyuan Nan
Xing Hu
Pengwei Jin
Shaohui Peng
Yuanbo Wen
Rui Zhang
Zidong Du

Though LLMs are capable of generating plausible programs, it’s challenging to interact with the LLMs further to revise the program, especially if the user’s specific requirements are different from the initial proposal. In this paper, we introduce ANPL, an interactive programming system that ensures users can always refine the generated code towards their specific programmatic intents via structureddecompositions. Borrowing the paradigm of sketching from program synthesis, an ANPL program consists of a set of input-outputs that it must satisfy, a “sketch” — control/data flow expressed in precise code (e. g. Python), and “holes” — sub-modules to be implemented by the LLM specified with natural language. The user revises an ANPL program by either modifying the sketch, changing the language used to describe the holes, or providing additional input-outputs to a particular hole, turning it into a sub-ANPL program that can be solved recursively. This workflow allows the users to offload programming burdens to the LLM as much as possible while retaining the ability to pinpoint and resolve bugs locally, without exposing the rest of the program to the LLM. We deploy ANPL on the Abstraction and Reasoning Corpus (ARC), a set of unique tasks that are challenging for state-of-the-art AI systems, showing it outperforms baseline programming systems that (a) without the ability to decompose tasks interactively and (b) without the guarantee that the modules can be correctly composed together. Additional evaluations on APPS, HumanEval, and real-world programming tasks have validated that the ANPL framework is applicable to multiple programming domains. We release the ANPL solutions to the ARC tasks as a dataset, providing insights into how humans decompose novel tasks programmatically.

PDF Details

ICLR Conference 2023 Conference Paper

BALTO: fast tensor program optimization with diversity-based active learning

Jun Bi
Xiaqing Li
Qi Guo 0001
Rui Zhang 0040
Yuanbo Wen 0001
Xing Hu 0001
Zidong Du
Xinkai Song

Tensor program optimization (TPO) based on pre-trained models can effectively reduce the computing time of deep neural networks. However, training of such models is prohibitively expensive, which highly depends on a large-scale dataset and thus requires tremendous time-consuming performance measurements (more than 1 million) on target platforms. In this paper, we propose BALTO, a fast TPO approach with biased-diversity-based active learning, aiming at reducing much lower training costs under similar optimization accuracy.The key insight is that random sampling of existing approaches suffers from a heavy redundancy of low-performance programs, which incurs tremendous duplicated time-consuming measurements. Inspired by this, BALTO removes such redundancy by introducing active learning (AL) to TPO for a much lower training cost. However, applying AL with a brute-force way in BALTO can lead to an overestimation problem. To address this, we further propose a biased-diversity-based diversity scheme specially designed for BALTO. We compare BALTO against TenSet on $6$ typical hardware platforms over $2$ learning models. Experimental results show that, on average, BALTO only requires 5% of the total performance measurements of TenSet to achieve the same or higher model accuracy. Moreover, the optimized tensor programs even outperform that of TenSet by 1.06% due to higher model accuracy.

Details

AAAI Conference 2023 Conference Paper

Conceptual Reinforcement Learning for Language-Conditioned Tasks

Shaohui Peng
Xing Hu
Rui Zhang
Jiaming Guo
Qi Yi
Ruizhi Chen
Zidong Du
Ling Li

Despite the broad application of deep reinforcement learning (RL), transferring and adapting the policy to unseen but similar environments is still a significant challenge. Recently, the language-conditioned policy is proposed to facilitate policy transfer through learning the joint representation of observation and text that catches the compact and invariant information across various environments. Existing studies of language-conditioned RL methods often learn the joint representation as a simple latent layer for the given instances (episode-specific observation and text), which inevitably includes noisy or irrelevant information and cause spurious correlations that are dependent on instances, thus hurting generalization performance and training efficiency. To address the above issue, we propose a conceptual reinforcement learning (CRL) framework to learn the concept-like joint representation for language-conditioned policy. The key insight is that concepts are compact and invariant representations in human cognition through extracting similarities from numerous instances in real-world. In CRL, we propose a multi-level attention encoder and two mutual information constraints for learning compact and invariant concepts. Verified in two challenging environments, RTFM and Messenger, CRL significantly improves the training efficiency (up to 70%) and generalization ability (up to 30%) to the new environment dynamics.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

Context Shift Reduction for Offline Meta-Reinforcement Learning

Yunkai Gao
Rui Zhang
Jiaming Guo
Fan Wu
Qi Yi
Shaohui Peng
Siming Lan
Ruizhi Chen

Offline meta-reinforcement learning (OMRL) utilizes pre-collected offline datasets to enhance the agent's generalization ability on unseen tasks. However, the context shift problem arises due to the distribution discrepancy between the contexts used for training (from the behavior policy) and testing (from the exploration policy). The context shift problem leads to incorrect task inference and further deteriorates the generalization ability of the meta-policy. Existing OMRL methods either overlook this problem or attempt to mitigate it with additional information. In this paper, we propose a novel approach called Context Shift Reduction for OMRL (CSRO) to address the context shift problem with only offline datasets. The key insight of CSRO is to minimize the influence of policy in context during both the meta-training and meta-test phases. During meta-training, we design a max-min mutual information representation learning mechanism to diminish the impact of the behavior policy on task representation. In the meta-test phase, we introduce the non-prior context collection strategy to reduce the effect of the exploration policy. Experimental results demonstrate that CSRO significantly reduces the context shift and improves the generalization ability, surpassing previous methods across various challenging domains.

PDF Details

NeurIPS Conference 2023 Conference Paper

Contrastive Modules with Temporal Attention for Multi-Task Reinforcement Learning

Siming Lan
Rui Zhang
Qi Yi
Jiaming Guo
Shaohui Peng
Yunkai Gao
Fan Wu
Ruizhi Chen

In the field of multi-task reinforcement learning, the modular principle, which involves specializing functionalities into different modules and combining them appropriately, has been widely adopted as a promising approach to prevent the negative transfer problem that performance degradation due to conflicts between tasks. However, most of the existing multi-task RL methods only combine shared modules at the task level, ignoring that there may be conflicts within the task. In addition, these methods do not take into account that without constraints, some modules may learn similar functions, resulting in restricting the model's expressiveness and generalization capability of modular methods. In this paper, we propose the Contrastive Modules with Temporal Attention(CMTA) method to address these limitations. CMTA constrains the modules to be different from each other by contrastive learning and combining shared modules at a finer granularity than the task level with temporal attention, alleviating the negative transfer within the task and improving the generalization ability and the performance for multi-task RL. We conducted the experiment on Meta-World, a multi-task RL benchmark containing various robotics manipulation tasks. Experimental results show that CMTA outperforms learning each task individually for the first time and achieves substantial performance improvements over the baselines.

PDF Details

NeurIPS Conference 2023 Conference Paper

Decompose a Task into Generalizable Subtasks in Multi-Agent Reinforcement Learning

Zikang Tian
Ruizhi Chen
Xing Hu
Ling Li
Rui Zhang
Fan Wu
Shaohui Peng
Jiaming Guo

In recent years, Multi-Agent Reinforcement Learning (MARL) techniques have made significant strides in achieving high asymptotic performance in single task. However, there has been limited exploration of model transferability across tasks. Training a model from scratch for each task can be time-consuming and expensive, especially for large-scale Multi-Agent Systems. Therefore, it is crucial to develop methods for generalizing the model across tasks. Considering that there exist task-independent subtasks across MARL tasks, a model that can decompose such subtasks from the source task could generalize to target tasks. However, ensuring true task-independence of subtasks poses a challenge. In this paper, we propose to \textbf{d}ecompose a \textbf{t}ask in\textbf{to} a series of \textbf{g}eneralizable \textbf{s}ubtasks (DT2GS), a novel framework that addresses this challenge by utilizing a scalable subtask encoder and an adaptive subtask semantic module. We show that these components endow subtasks with two properties critical for task-independence: avoiding overfitting to the source task and maintaining consistent yet scalable semantics across tasks. Empirical results demonstrate that DT2GS possesses sound zero-shot generalization capability across tasks, exhibits sufficient transferability, and outperforms existing methods in both multi-task and single-task problems.

PDF Details

NeurIPS Conference 2023 Conference Paper

Efficient Symbolic Policy Learning with Differentiable Symbolic Expression

Jiaming Guo
Rui Zhang
Shaohui Peng
Qi Yi
Xing Hu
Ruizhi Chen
Zidong Du
Xishan Zhang

Deep reinforcement learning (DRL) has led to a wide range of advances in sequential decision-making tasks. However, the complexity of neural network policies makes it difficult to understand and deploy with limited computational resources. Currently, employing compact symbolic expressions as symbolic policies is a promising strategy to obtain simple and interpretable policies. Previous symbolic policy methods usually involve complex training processes and pre-trained neural network policies, which are inefficient and limit the application of symbolic policies. In this paper, we propose an efficient gradient-based learning method named Efficient Symbolic Policy Learning (ESPL) that learns the symbolic policy from scratch in an end-to-end way. We introduce a symbolic network as the search space and employ a path selector to find the compact symbolic policy. By doing so we represent the policy with a differentiable symbolic expression and train it in an off-policy manner which further improves the efficiency. In addition, in contrast with previous symbolic policies which only work in single-task RL because of complexity, we expand ESPL on meta-RL to generate symbolic policies for unseen tasks. Experimentally, we show that our approach generates symbolic policies with higher performance and greatly improves data efficiency for single-task RL. In meta-RL, we demonstrate that compared with neural network policies the proposed symbolic policy achieves higher performance and efficiency and shows the potential to be interpretable.

PDF Details

NeurIPS Conference 2023 Conference Paper

Emergent Communication for Rules Reasoning

Yuxuan Guo
Yifan Hao
Rui Zhang
Enshuai Zhou
Zidong Du
Xishan Zhang
Xinkai Song
Yuanbo Wen

Research on emergent communication between deep-learning-based agents has received extensive attention due to its inspiration for linguistics and artificial intelligence. However, previous attempts have hovered around emerging communication under perception-oriented environmental settings, that forces agents to describe low-level perceptual features intra image or symbol contexts. In this work, inspired by the classic human reasoning test (namely Raven's Progressive Matrix), we propose the Reasoning Game, a cognition-oriented environment that encourages agents to reason and communicate high-level rules, rather than perceived low-level contexts. Moreover, we propose 1) an unbiased dataset (namely rule-RAVEN) as a benchmark to avoid overfitting, 2) and a two-stage curriculum agent training method as a baseline for more stable convergence in the Reasoning Game, where contexts and semantics are bilaterally drifting. Experimental results show that, in the Reasoning Game, a semantically stable and compositional language emerges to solve reasoning problems. The emerged language helps agents apply the extracted rules to the generalization of unseen context attributes, and to the transfer between different context attributes or even tasks.

PDF Details

ICML Conference 2023 Conference Paper

Online Prototype Alignment for Few-shot Policy Transfer

Qi Yi
Rui Zhang 0040
Shaohui Peng
Jiaming Guo
Yunkai Gao 0001
Kaizhao Yuan
Ruizhi Chen
Siming Lan

Domain adaptation in RL mainly deals with the changes of observation when transferring the policy to a new environment. Many traditional approaches of domain adaptation in RL manage to learn a mapping function between the source and target domain in explicit or implicit ways. However, they typically require access to abundant data from the target domain. Besides, they often rely on visual clues to learn the mapping function and may fail when the source domain looks quite different from the target domain. To address these problems, in this paper, we propose a novel framework Online Prototype Alignment (OPA) to learn the mapping function based on the functional similarity of elements and is able to achieve few-shot policy transfer within only several episodes. The key insight of OPA is to introduce an exploration mechanism that can interact with the unseen elements of the target domain in an efficient and purposeful manner, and then connect them with the seen elements in the source domain according to their functionalities (instead of visual clues). Experimental results show that when the target domain looks visually different from the source domain, OPA can achieve better transfer performance even with much fewer samples from the target domain, outperforming prior methods.

Details

AAAI Conference 2023 Conference Paper

Online Symbolic Regression with Informative Query

Pengwei Jin
Di Huang
Rui Zhang
Xing Hu
Ziyuan Nan
Zidong Du
Qi Guo
Yunji Chen

Symbolic regression, the task of extracting mathematical expressions from the observed data, plays a crucial role in scientific discovery. Despite the promising performance of existing methods, most of them conduct symbolic regression in an offline setting. That is, they treat the observed data points as given ones that are simply sampled from uniform distributions without exploring the expressive potential of data. However, for real-world scientific problems, the data used for symbolic regression are usually actively obtained by doing experiments, which is an online setting. Thus, how to obtain informative data that can facilitate the symbolic regression process is an important problem that remains challenging. In this paper, we propose QUOSR, a query-based framework for online symbolic regression that can automatically obtain informative data in an iterative manner. Specifically, at each step, QUOSR receives historical data points, generates new x, and then queries the symbolic expression to get the corresponding y, where the (x, y) serves as new data points. This process repeats until the maximum number of query steps is reached. To make the generated data points informative, we implement the framework with a neural network and train it by maximizing the mutual information between generated data points and the target expression. Through comprehensive experiments, we show that QUOSR can facilitate modern symbolic regression methods by generating informative data.

PDF Details DOI

NeurIPS Conference 2022 Conference Paper

Accelerating Sparse Convolution with Column Vector-Wise Sparsity

Yijun Tan
Kai Han
Kang Zhao
Xianzhi Yu
Zidong Du
Yunji Chen
Yunhe Wang
Jun Yao

Weight sparsity is a promising approach to reducing the model size and computation cost of convolutional neural networks (CNNs). Nevertheless, non-zero weights often distribute randomly in sparse CNN models, introducing enormous difficulty in obtaining actual speedup on common hardware (e. g. , GPU) over their dense counterparts. Existing acceleration solutions either require hardware modifications for irregular memory access support or rely on a partially structured sparsity pattern. Neither of these methods is capable of achieving fruitful speedup on convolution layers. In this work, we propose an algorithm-software co-designed sparse convolution based on a novel out-vector-wise (OVW) sparse pattern. Building on the insight that vertical vector integrity can preserve continuous memory access in IM2COL, the OVW pattern treats a $V\times1$ vector as an entirety. To reduce the error caused by sparsity, we propose an equivalent transformation process, i. e. , clustering-based channel permutation, to gather similar rows together. Experimental evaluations demonstrate that our method achieves a $1. 7\times$ and $3. 2\times$ speedup over the SOTA solution and the dense convolution of ResNet50 on NVIDIA V100 at 75\% sparsity, respectively, with only negligible accuracy loss. Moreover, compared to the SOTA solution that achieves speedups only on data with 60\% sparsity or more, our method begins to obtain speedups on data with only 10\% sparsity.

PDF Details

ICML Conference 2022 Conference Paper

BabelTower: Learning to Auto-parallelized Program Translation

Yuanbo Wen 0001
Qi Guo 0001
Qiang Fu
Xiaqing Li
Jianxing Xu
Yanlin Tang
Yongwei Zhao 0001
Xing Hu 0001

GPUs have become the dominant computing platforms for many applications, while programming GPUs with the widely-used CUDA parallel programming model is difficult. As sequential C code is relatively easy to obtain either from legacy repositories or by manual implementation, automatically translating C to its parallel CUDA counterpart is promising to relieve the burden of GPU programming. However, because of huge differences between the sequential C and the parallel CUDA programming model, existing approaches fail to conduct the challenging auto-parallelized program translation. In this paper, we propose a learning-based framework, i. e. , BabelTower, to address this problem. We first create a large-scale dataset consisting of compute-intensive function-level monolingual corpora. We further propose using back-translation with a discriminative reranker to cope with unpaired corpora and parallel semantic conversion. Experimental results show that BabelTower outperforms state-of-the-art by 1. 79, 6. 09, and 9. 39 in terms of BLEU, CodeBLEU, and specifically designed ParaBLEU, respectively. The CUDA code generated by BabelTower attains a speedup of up to 347x over the sequential C code, and the developer productivity is improved by at most 3. 8x.

Details

NeurIPS Conference 2022 Conference Paper

Causality-driven Hierarchical Structure Discovery for Reinforcement Learning

Shaohui Peng
Xing Hu
Rui Zhang
Ke Tang
Jiaming Guo
Qi Yi
Ruizhi Chen
Xishan Zhang

Hierarchical reinforcement learning (HRL) has been proven to be effective for tasks with sparse rewards, for it can improve the agent's exploration efficiency by discovering high-quality hierarchical structures (e. g. , subgoals or options). However, automatically discovering high-quality hierarchical structures is still a great challenge. Previous HRL methods can only find the hierarchical structures in simple environments, as they are mainly achieved through the randomness of agent's policies during exploration. In complicated environments, such a randomness-driven exploration paradigm can hardly discover high-quality hierarchical structures because of the low exploration efficiency. In this paper, we propose CDHRL, a causality-driven hierarchical reinforcement learning framework, to build high-quality hierarchical structures efficiently in complicated environments. The key insight is that the causalities among environment variables are naturally fit for modeling reachable subgoals and their dependencies; thus, the causality is suitable to be the guidance in building high-quality hierarchical structures. Roughly, we build the hierarchy of subgoals based on causality autonomously, and utilize the subgoal-based policies to unfold further causality efficiently. Therefore, CDHRL leverages a causality-driven discovery instead of a randomness-driven exploration for high-quality hierarchical structure construction. The results in two complex environments, 2D-Minecraft and Eden, show that CDHRL can discover high-quality hierarchical structures and significantly enhance exploration efficiency.

PDF Details

ICLR Conference 2022 Conference Paper

Neural Program Synthesis with Query

Di Huang
Rui Zhang 0040
Xing Hu 0001
Xishan Zhang
Pengwei Jin
Nan Li
Zidong Du
Qi Guo 0001

Aiming to find a program satisfying the user intent given input-output examples, program synthesis has attracted increasing interest in the area of machine learning. Despite the promising performance of existing methods, most of their success comes from the privileged information of well-designed input-output examples. However, providing such input-output examples is unrealistic because it requires the users to have the ability to describe the underlying program with a few input-output examples under the training distribution. In this work, we propose a query-based framework that trains a query neural network to generate informative input-output examples automatically and interactively from a large query space. The quality of the query depends on the amount of the mutual information between the query and the corresponding program, which can guide the optimization of the query framework. To estimate the mutual information more accurately, we introduce the functional space (F-space) which models the relevance between the input-output examples and the programs in a differentiable way. We evaluate the effectiveness and generalization of the proposed query-based framework on the Karel task and the list processing task. Experimental results show that the query-based framework can generate informative input-output examples which achieve and even outperform well-designed input-output examples.

Details

NeurIPS Conference 2022 Conference Paper

Object-oriented reinforcement learning (OORL) is a promising way to improve the sample efficiency and generalization ability over standard RL. Recent works that try to solve OORL tasks without additional feature engineering mainly focus on learning the object representations and then solving tasks via reasoning based on these object representations. However, none of these works tries to explicitly model the inherent similarity between different object instances of the same category. Objects of the same category should share similar functionalities; therefore, the category is the most critical property of an object. Following this insight, we propose a novel framework named Object-Category Aware Reinforcement Learning (OCARL), which utilizes the category information of objects to facilitate both perception and reasoning. OCARL consists of three parts: (1) Category-Aware Unsupervised Object Discovery (UOD), which discovers the objects as well as their corresponding categories; (2) Object-Category Aware Perception, which encodes the category information and is also robust to the incompleteness of (1) at the same time; (3) Object-Centric Modular Reasoning, which adopts multiple independent and object-category-specific networks when reasoning based on objects. Our experiments show that OCARL can improve both the sample efficiency and generalization in the OORL domain.

PDF Details

IJCAI Conference 2021 Conference Paper

Hindsight Value Function for Variance Reduction in Stochastic Dynamic Environment

Jiaming Guo
Rui Zhang
Xishan Zhang
Shaohui Peng
Qi Yi
Zidong Du
Xing Hu
Qi Guo

Policy gradient methods are appealing in deep reinforcement learning but suffer from high variance of gradient estimate. To reduce the variance, the state value function is applied commonly. However, the effect of the state value function becomes limited in stochastic dynamic environments, where the unexpected state dynamics and rewards will increase the variance. In this paper, we propose to replace the state value function with a novel hindsight value function, which leverages the information from the future to reduce the variance of the gradient estimate for stochastic dynamic environments. Particularly, to obtain an ideally unbiased gradient estimate, we propose an information-theoretic approach, which optimizes the embeddings of the future to be independent of previous actions. In our experiments, we apply the proposed hindsight value function in stochastic dynamic environments, including discrete-action environments and continuous-action environments. Compared with the standard state value function, the proposed hindsight value function consistently reduces the variance, stabilizes the training, and improves the eventual policy.

PDF Details DOI

NeurIPS Conference 2021 Conference Paper

ScaleCert: Scalable Certified Defense against Adversarial Patches with Sparse Superficial Layers

Husheng Han
Kaidi Xu
Xing Hu
Xiaobing Chen
Ling Liang
Zidong Du
Qi Guo
Yanzhi Wang

Adversarial patch attacks that craft the pixels in a confined region of the input images show their powerful attack effectiveness in physical environments even with noises or deformations. Existing certified defenses towards adversarial patch attacks work well on small images like MNIST and CIFAR-10 datasets, but achieve very poor certified accuracy on higher-resolution images like ImageNet. It is urgent to design both robust and effective defenses against such a practical and harmful attack in industry-level larger images. In this work, we propose the certified defense methodology that achieves high provable robustness for high-resolution images and largely improves the practicality for real adoption of the certified defense. The basic insight of our work is that the adversarial patch intends to leverage localized superficial important neurons (SIN) to manipulate the prediction results. Hence, we leverage the SIN-based DNN compression techniques to significantly improve the certified accuracy, by reducing the adversarial region searching overhead and filtering the prediction noises. Our experimental results show that the certified accuracy is increased from 36. 3% (the state-of-the-art certified detection) to 60. 4%on the ImageNet dataset, largely pushing the certified defenses for practical use.

PDF Details

AAAI Conference 2020 Conference Paper

DWM: A Decomposable Winograd Method for Convolution Acceleration

Di Huang
Xishan Zhang
Rui Zhang
Tian Zhi
Deyuan He
Jiaming Guo
Chang Liu
Qi Guo

Winograd’s minimal ﬁltering algorithm has been widely used in Convolutional Neural Networks (CNNs) to reduce the number of multiplications for faster processing. However, it is only effective on convolutions with kernel size as 3x3 and stride as 1, because it suffers from signiﬁcantly increased FLOPs and numerical accuracy problem for kernel size larger than 3x3 and fails on convolution with stride larger than 1. In this paper, we propose a novel Decomposable Winograd Method (DWM), which breaks through the limitation of original Winograd’s minimal ﬁltering algorithm to a wide and general convolutions. DWM decomposes kernels with large size or large stride to several small kernels with stride as 1 for further applying Winograd method, so that DWM can reduce the number of multiplications while keeping the numerical accuracy. It enables the fast exploring of larger kernel size and larger stride value in CNNs for high performance and accuracy and even the potential for new CNNs. Comparing against the original Winograd, the proposed DWM is able to support all kinds of convolutions with a speedup of ∼2, without affecting the numerical accuracy.

PDF Details

AAAI Conference 2019 Conference Paper

TDSNN: From Deep Neural Networks to Deep Spike Neural Networks with Temporal-Coding

Lei Zhang
Shengyuan Zhou
Tian Zhi
Zidong Du
Yunji Chen

Continuous-valued deep convolutional networks (DNNs) can be converted into accurate rate-coding based spike neural networks (SNNs). However, the substantial computational and energy costs, which is caused by multiple spikes, limit their use in mobile and embedded applications. And recent works have shown that the newly emerged temporal-coding based SNNs converted from DNNs can reduce the computational load effectively. In this paper, we propose a novel method to convert DNNs to temporal-coding SNNs, called TDSNN. Combined with the characteristic of the leaky integrate-andfire (LIF) neural model, we put forward a new coding principle Reverse Coding and design a novel Ticking Neuron mechanism. According to our evaluation, our proposed method achieves 42% total operations reduction on average in large networks comparing with DNNs with no more than 0. 5% accuracy loss. The evaluation shows that TDSNN may prove to be one of the key enablers to make the adoption of SNNs widespread.

PDF Details