Author name cluster

Vikas Chandra

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.

12 papers

2 author rows

ICML Conference 2025 Conference Paper

Agent-as-a-Judge: Evaluate Agents with Agents

Mingchen Zhuge
Changsheng Zhao 0002
Dylan R. Ashley
Wenyi Wang
Dmitrii Khizbullin
Yunyang Xiong
Zechun Liu
Ernie Chang

Contemporary evaluation techniques are inadequate for agentic systems. These approaches either focus exclusively on final outcomes—ignoring the step-by-step nature of the thinking done by agentic systems—or require excessive manual labour. To address this, we introduce the Agent-as-a-Judge framework, wherein agentic systems are used to evaluate agentic systems. This is a natural extension of the LLM-as-a-Judge framework, incorporating agentic features that enable intermediate feedback for the entire task-solving processes for more precise evaluations. We apply the Agent-as-a-Judge framework to the task of code generation. To overcome issues with existing benchmarks and provide a proof-of-concept testbed for Agent-as-a-Judge, we present DevAI, a new benchmark of 55 realistic AI code generation tasks. DevAI includes rich manual annotations, like a total of 365 hierarchical solution requirements, which make it particularly suitable for an agentic evaluator. We benchmark three of the top code-generating agentic systems using Agent-as-a-Judge and find that our framework dramatically outperforms LLM-as-a-Judge and is as reliable as our human evaluation baseline. Altogether, we believe that this work represents a concrete step towards enabling vastly more sophisticated agentic systems. To help that, our dataset and the full implementation of Agent-as-a-Judge will be publically available at https: //github. com/metauto-ai/agent-as-a-judge

Details

ICML Conference 2025 Conference Paper

LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding

Xiaoqian Shen
Yunyang Xiong
Changsheng Zhao 0002
Lemeng Wu
Jun Chen 0021
Chenchen Zhu
Zechun Liu
Fanyi Xiao

Multimodal Large Language Models (MLLMs) have shown promising progress in understanding and analyzing video content. However, processing long videos remains a significant challenge constrained by LLM’s context size. To address this limitation, we propose LongVU, a spatiotemporal adaptive compression mechanism that reduces the number of video tokens while preserving visual details of long videos. Our idea is based on leveraging cross-modal query and inter-frame dependencies to adaptively reduce temporal and spatial redundancy in videos. Specifically, we leverage DINOv2 features to remove redundant frames that exhibit high similarity. Then we utilize text-guided cross-modal query for selective frame feature reduction. Further, we perform spatial token reduction across frames based on their temporal dependencies. Our adaptive compression strategy effectively processes a large number of frames with little visual information loss within given context length. Our LongVU consistently surpass existing methods across a variety of video understanding benchmarks, especially on hour-long video understanding tasks such as VideoMME and MLVU. Given a light-weight LLM, our LongVU also scales effectively into a smaller size with state-of-the-art video understanding performance.

Details

NeurIPS Conference 2025 Conference Paper

ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantization

Zechun Liu
Changsheng Zhao
Hanxian Huang
Sijia Chen
Jing Zhang
Jiawei Zhao
Scott Roy
Lisa Jin

The optimal bit-width for achieving the best trade-off between quantized model size and accuracy has been a subject of ongoing debate. While some advocate for 4-bit quantization, others propose that 1. 58-bit offers superior results. However, the lack of a cohesive framework for different bits has left such conclusions relatively tenuous. We present ParetoQ, the first unified framework that facilitates rigorous comparisons across 1-bit, 1. 58-bit, 2-bit, 3-bit, and 4-bit quantization settings. Our findings reveal a notable learning transition between 2 and 3 bits: For 3-bits and above, the fine-tuned models stay close to their original pre-trained distributions, whereas for learning 2-bit networks or below, the representations change drastically. By optimizing training schemes and refining quantization functions, ParetoQ surpasses all previous methods tailored to specific bit widths. Remarkably, our ParetoQ ternary 600M-parameter model even outperforms the previous SoTA ternary 3B-parameter model in accuracy, using only one-fifth of the parameters. Extensive experimentation shows that ternary, 2-bit, and 3-bit quantization maintains comparable performance in the size-accuracy trade-off and generally exceeds 4-bit and binary quantization. Considering hardware constraints, 2-bit quantization offers promising potential for memory reduction and speedup.

PDF Details

ICLR Conference 2025 Conference Paper

SpinQuant: LLM Quantization with Learned Rotations

Zechun Liu
Changsheng Zhao 0002
Igor Fedorov
Bilge Soran
Dhruv Choudhary
Raghuraman Krishnamoorthi
Vikas Chandra
Yuandong Tian

Post-training quantization (PTQ) techniques applied to weights, activations, and the KV cache greatly reduce memory usage, latency, and power consumption of Large Language Models (LLMs), but may lead to large quantization errors when outliers are present. Rotating activation or weight matrices helps remove outliers and benefits quantization. In this work, we identify a collection of applicable rotation parameterizations that lead to identical outputs in full-precision Transformer architectures while enhancing quantization accuracy. In addition, we find that some random rotations lead to much better quantization than others, with an up to 13 points difference in downstream zero-shot reasoning performance. As a result, we propose SpinQuant, a novel approach that incorporates learned rotation matrices for optimal quantized network accuracy. With 4-bit quantization of weight, activation, and KV-cache, SpinQuant narrows the accuracy gap on zero-shot reasoning tasks with full precision to merely 2.9 points on the LLaMA-2 7B model, surpassing LLM-QAT by 19.1 points and SmoothQuant by 25.0 points. Furthermore, SpinQuant also outperforms concurrent work QuaRot, which applies random rotations to remove outliers. In particular, for LLaMA-3 8B models that are hard to quantize, SpinQuant reduces the gap to full precision by up to 45.1% relative to QuaRot. Code is available at https://github.com/facebookresearch/SpinQuant.

Details

TMLR Journal 2025 Journal Article

Streamlining Language Models via Semantic Basis Analysis

Yang Li
Daniel Agyei Asante
Changsheng Zhao
Ernie Chang
Yangyang Shi
Vikas Chandra

As the size of language models increases, they deliver substantial performance improvements across a variety of applications. However, this growth also leads to greater computational demands, making deployment on resource-constrained devices—such as personal computers and mobile or wearable devices—more challenging, and significantly raising inference costs on cloud servers. To address these challenges, we introduce Basel, a method to streamline language models by leveraging the semantic structure of their weight matrices. Specifically, Basel treats each weight matrix as a linear combination of bases, selectively retaining those that are associated with essential semantics for the target application, pruning redundant ones, and introducing new bases that enhance task performance. Experimental results demonstrate that Basel achieves significant model size reduction compared to baseline techniques, while maintaining comparable or even superior accuracy across diverse applications.

PDF Details

ICML Conference 2024 Conference Paper

MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases

Zechun Liu
Changsheng Zhao 0002
Forrest N. Iandola
Chen Lai
Yuandong Tian
Igor Fedorov
Yunyang Xiong
Ernie Chang

This paper addresses the growing need for efficient large language models (LLMs) on mobile devices, driven by increasing cloud costs and latency concerns. We focus on designing top-quality LLMs with fewer than a billion parameters, a practical choice for mobile deployment. Contrary to prevailing belief emphasizing the pivotal role of data and parameter quantity in determining model quality, our investigation underscores the significance of model architecture for sub-billion scale LLMs. Leveraging deep and thin architectures, coupled with embedding sharing and grouped-query attention mechanisms, we establish a strong baseline network denoted as MobileLLM, which attains a remarkable 2. 7%/4. 3% accuracy boost over preceding 125M/350M state-of-the-art models. Additionally, we propose an immediate block-wise weight-sharing approach with no increase in model size and only marginal latency overhead. The resultant models, denoted as MobileLLM-LS, demonstrate a further accuracy enhancement of 0. 7%/0. 8% than MobileLLM 125M/350M. Moreover, MobileLLM model family shows significant improvements compared to previous sub-billion models on chat benchmarks, and demonstrates close correctness to LLaMA-v2 7B in API calling tasks, highlighting the capability of small models for common on-device use cases.

Details

ICML Conference 2022 Conference Paper

DepthShrinker: A New Compression Paradigm Towards Boosting Real-Hardware Efficiency of Compact Neural Networks

Yonggan Fu
Haichuan Yang
Jiayi Yuan 0001
Meng Li 0004
Cheng Wan 0005
Raghuraman Krishnamoorthi
Vikas Chandra
Yingyan Celine Lin

Efficient deep neural network (DNN) models equipped with compact operators (e. g. , depthwise convolutions) have shown great potential in reducing DNNs’ theoretical complexity (e. g. , the total number of weights/operations) while maintaining a decent model accuracy. However, existing efficient DNNs are still limited in fulfilling their promise in boosting real-hardware efficiency, due to their commonly adopted compact operators’ low hardware utilization. In this work, we open up a new compression paradigm for developing real-hardware efficient DNNs, leading to boosted hardware efficiency while maintaining model accuracy. Interestingly, we observe that while some DNN layers’ activation functions help DNNs’ training optimization and achievable accuracy, they can be properly removed after training without compromising the model accuracy. Inspired by this observation, we propose a framework dubbed DepthShrinker, which develops hardware-friendly compact networks via shrinking the basic building blocks of existing efficient DNNs that feature irregular computation patterns into dense ones with much improved hardware utilization and thus real-hardware efficiency. Excitingly, our DepthShrinker framework delivers hardware-friendly compact networks that outperform both state-of-the-art efficient DNNs and compression techniques, e. g. , a 3. 06% higher accuracy and 1. 53x throughput on Tesla V100 over SOTA channel-wise pruning method MetaPruning. Our codes are available at: https: //github. com/facebookresearch/DepthShrinker.

Details

ICLR Conference 2022 Conference Paper

NASViT: Neural Architecture Search for Efficient Vision Transformers with Gradient Conflict aware Supernet Training

Chengyue Gong
Dilin Wang
Meng Li 0004
Xinlei Chen
Zhicheng Yan 0001
Yuandong Tian
Qiang Liu 0001
Vikas Chandra

Designing accurate and efficient vision transformers (ViTs) is a highly important but challenging task. Supernet-based one-shot neural architecture search (NAS) enables fast architecture optimization and has achieved state-of-the-art (SOTA) results on convolutional neural networks (CNNs). However, directly applying the supernet-based NAS to optimize ViTs leads to poor performance - even worse compared to training single ViTs. In this work, we observe that the poor performance is due to a gradient conflict issue: the gradients of different sub-networks conflict with that of the supernet more severely in ViTs than CNNs, which leads to early saturation in training and inferior convergence. To alleviate this issue, we propose a series of techniques, including a gradient projection algorithm, a switchable layer scaling design, and a simplified data augmentation and regularization training recipe. The proposed techniques significantly improve the convergence and the performance of all sub-networks. Our discovered hybrid ViT model family, dubbed NASViT, achieves top-1 accuracy from 78.2% to 81.8% on ImageNet from 200M to 800M FLOPs, and outperforms all the prior art CNNs and ViTs, including AlphaNet and LeViT, etc. When transferred to semantic segmentation tasks, NASViTs also outperform previous backbones on both Cityscape and ADE20K datasets, achieving 73.2% and 37.9% mIoU with only 5G FLOPs, respectively. Code is available at https://github.com/facebookresearch/NASViT.

Details

ICML Conference 2021 Conference Paper

AlphaNet: Improved Training of Supernets with Alpha-Divergence

Dilin Wang
Chengyue Gong
Meng Li 0004
Qiang Liu 0001
Vikas Chandra

Weight-sharing neural architecture search (NAS) is an effective technique for automating efficient neural architecture design. Weight-sharing NAS builds a supernet that assembles all the architectures as its sub-networks and jointly trains the supernet with the sub-networks. The success of weight-sharing NAS heavily relies on distilling the knowledge of the supernet to the sub-networks. However, we find that the widely used distillation divergence, i. e. , KL divergence, may lead to student sub-networks that over-estimate or under-estimate the uncertainty of the teacher supernet, leading to inferior performance of the sub-networks. In this work, we propose to improve the supernet training with a more generalized alpha-divergence. By adaptively selecting the alpha-divergence, we simultaneously prevent the over-estimation or under-estimation of the uncertainty of the teacher model. We apply the proposed alpha-divergence based supernets training to both slimmable neural networks and weight-sharing NAS, and demonstrate significant improvements. Specifically, our discovered model family, AlphaNet, outperforms prior-art models on a wide range of FLOPs regimes, including BigNAS, Once-for-All networks, and AttentiveNAS. We achieve ImageNet top-1 accuracy of 80. 0% with only 444M FLOPs. Our code and pretrained models are available at https: //github. com/facebookresearch/AlphaNet.

Details

ICLR Conference 2021 Conference Paper

CPT: Efficient Deep Neural Network Training via Cyclic Precision

Yonggan Fu
Han Guo
Meng Li 0004
Xin Yang
Yining Ding
Vikas Chandra
Yingyan Celine Lin

Low-precision deep neural network (DNN) training has gained tremendous attention as reducing precision is one of the most effective knobs for boosting DNNs' training time/energy efficiency. In this paper, we attempt to explore low-precision training from a new perspective as inspired by recent findings in understanding DNN training: we conjecture that DNNs' precision might have a similar effect as the learning rate during DNN training, and advocate dynamic precision along the training trajectory for further boosting the time/energy efficiency of DNN training. Specifically, we propose Cyclic Precision Training (CPT) to cyclically vary the precision between two boundary values which can be identified using a simple precision range test within the first few training epochs. Extensive simulations and ablation studies on five datasets and eleven models demonstrate that CPT's effectiveness is consistent across various models/tasks (including classification and language modeling). Furthermore, through experiments and visualization we show that CPT helps to (1) converge to a wider minima with a lower generalization error and (2) reduce training variance which we believe opens up a new design knob for simultaneously improving the optimization and efficiency of DNN training.

Details

ICML Conference 2021 Conference Paper

Double-Win Quant: Aggressively Winning Robustness of Quantized Deep Neural Networks via Random Precision Training and Inference

Yonggan Fu
Qixuan Yu 0001
Meng Li 0004
Vikas Chandra
Yingyan Celine Lin

Quantization is promising in enabling powerful yet complex deep neural networks (DNNs) to be deployed into resource constrained platforms. However, quantized DNNs are vulnerable to adversarial attacks unless being equipped with sophisticated techniques, leading to a dilemma of struggling between DNNs’ efficiency and robustness. In this work, we demonstrate a new perspective regarding quantization’s role in DNNs’ robustness, advocating that quantization can be leveraged to largely boost DNNs’ robustness, and propose a framework dubbed Double-Win Quant that can boost the robustness of quantized DNNs over their full precision counterparts by a large margin. Specifically, we for the first time identify that when an adversarially trained model is quantized to different precisions in a post-training manner, the associated adversarial attacks transfer poorly between different precisions. Leveraging this intriguing observation, we further develop Double-Win Quant integrating random precision inference and training to further reduce and utilize the poor adversarial transferability, enabling an aggressive “win-win" in terms of DNNs’ robustness and efficiency. Extensive experiments and ablation studies consistently validate Double-Win Quant’s effectiveness and advantages over state-of-the-art (SOTA) adversarial training methods across various attacks/models/datasets. Our codes are available at: https: //github. com/RICE-EIC/Double-Win-Quant.

Details

AAAI Conference 2021 Conference Paper

NASGEM: Neural Architecture Search via Graph Embedding Method

Hsin-Pai Cheng
Tunhou Zhang
Yixing Zhang
Shiyu Li
Feng Liang
Feng Yan
Meng Li
Vikas Chandra

Neural Architecture Search (NAS) automates and prospers the design of neural networks. Estimator-based NAS has been proposed recently to model the relationship between architectures and their performance to enable scalable and flexible search. However, existing estimator-based methods encode the architecture into a latent space without considering graph similarity. Ignoring graph similarity in node-based search space may induce a large inconsistency between similar graphs and their distance in the continuous encoding space, leading to inaccurate encoding representation and/or reduced representation capacity that can yield sub-optimal search results. To preserve graph correlation information in encoding, we propose NAS- GEM which stands for Neural Architecture Search via Graph Embedding Method. NASGEM is driven by a novel graph embedding method equipped with similarity measures to capture the graph topology information. By precisely estimating the graph distance and using an auxiliary Weisfeiler-Lehman kernel to guide the encoding, NASGEM can utilize additional structural information to get more accurate graph representation to improve the search efficiency. GEMNet, a set of networks discovered by NASGEM, consistently outperforms networks crafted by existing search methods in classification tasks, i. e. , with 0. 4%-3. 6% higher accuracy while having 11%- 21% fewer Multiply-Accumulates. We further transfer GEM- Net for COCO object detection. In both one-stage and twostage detectors, our GEMNet surpasses its manually-crafted and automatically-searched counterparts.

PDF Details