4.4k citations · 6.9k across the 45 of their papers we have counts for
46 papers
Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks
Mengyu Zheng, Kai Han, Boxun Li +13
The software engineering capabilities of general-purpose agent harnesses remain underexplored, and existing benchmarks offer limited support for comparing these harnesses under con…
Adversarial Error Correction for Visual Autoregressive Generation
Ligong Bi, Tao Huang, Jianyuan Guo +1
Visual Autoregressive (VAR) models have emerged as a powerful paradigm for image synthesis by performing hierarchical next-scale prediction. However, VAR models are inherently pron…
Sibyl-AutoResearch: Autonomous Research Needs Self-Evolving Trial-and-Error Harnesses, Not Paper Generators
Chengcheng Wang, Qinhua Xie, Wei He +3
Autonomous research systems increasingly make the scientific workflow executable: agents can propose ideas, run code, inspect results, and draft papers. But executable workflows do…
LCGNav: Local Candidate-Aware Geometric Enhancement for General Topological Planning in Vision-Language Navigation
Jiankun Peng, Jianyuan Guo, Yiguang Yang +3
Online topological planning has become an effective paradigm for Vision-Language Navigation in Continuous Environments (VLN-CE), but existing methods still suffer from two limitati…
PA-Attack: Guiding Gray-Box Attacks on LVLM Vision Encoders with Prototypes and Attention
Hefei Mei, Zirui Wang, Chang Xu +2
Large Vision-Language Models (LVLMs) are foundational to modern multimodal applications, yet their susceptibility to adversarial attacks remains a critical concern. Prior white-box…
KTV: Keyframes and Key Tokens Selection for Efficient Training-Free Video LLMs
Baiyang Song, Jun Peng, Yuxin Zhang +3
Training-free video understanding leverages the strong image comprehension capabilities of pre-trained vision language models (VLMs) by treating a video as a sequence of static fra…
Dynamic Topology Awareness: Breaking the Granularity Rigidity in Vision-Language Navigation
Jiankun Peng, Jianyuan Guo, Ying Xu +5
Vision-Language Navigation in Continuous Environments (VLN-CE) presents a core challenge: grounding high-level linguistic instructions into precise, safe, and long-horizon spatial…
ScaleNet: Scaling up Pretrained Neural Networks with Incremental Parameters
Zhiwei Hao, Jianyuan Guo, Li Shen +4
Recent advancements in vision transformers (ViTs) have demonstrated that larger models often achieve superior performance. However, training these models remains computationally in…
ADSeeker: A Knowledge-Grounded Reasoning Framework for Industry Anomaly Detection and Reasoning
Kai Zhang, Zekai Zhang, Xihe Sun +6
Automatic vision inspection holds significant importance in industry inspection. While multimodal large language models (MLLMs) exhibit strong language understanding capabilities a…
Bridging Sign and Spoken Languages: Pseudo Gloss Generation for Sign Language Translation
Jianyuan Guo, Peike Li, Trevor Cohn
Sign Language Translation (SLT) aims to map sign language videos to spoken language text. A common approach relies on gloss annotations as an intermediate representation, decomposi…
Circle-RoPE: Cone-like Decoupled Rotary Positional Embedding for Large Vision-Language Models
Chengcheng Wang, Jianyuan Guo, Hongguang Li +4
Rotary Position Embedding (RoPE) is widely adopted in large language models, but when applied to vision-language models (VLMs) it couples text and image position indices and can in…
Free Video-LLM: Prompt-guided Visual Perception for Efficient Training-free Video LLMs
Kai Han, Jianyuan Guo, Yehui Tang +3
Vision-language large models have achieved remarkable success in various multi-modal tasks, yet applying them to video understanding remains challenging due to the inherent complex…
Token Compensator: Altering Inference Cost of Vision Transformer without Re-Tuning
Shibo Jie, Yehui Tang, Jianyuan Guo +3
Token compression expedites the training and inference of Vision Transformers (ViTs) by reducing the number of the redundant tokens, e.g., pruning inattentive tokens or merging sim…
GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer
Ding Jia, Jianyuan Guo, Kai Han +4
Cross-modal transformers have demonstrated superiority in various vision tasks by effectively integrating different modalities. This paper first critiques prior token exchange meth…
Data-efficient Large Vision Models through Sequential Autoregression
Jianyuan Guo, Zhiwei Hao, Chengcheng Wang +5
Training general-purpose vision models on purely sequential visual data, eschewing linguistic inputs, has heralded a new frontier in visual understanding. These models are intended…
Vision Superalignment: Weak-to-Strong Generalization for Vision Foundation Models
Jianyuan Guo, Hanting Chen, Chengcheng Wang +3
Recent advancements in large language models have sparked interest in their extraordinary and near-superhuman capabilities, leading researchers to explore methods for evaluating an…
SAM-DiffSR: Structure-Modulated Diffusion Model for Image Super-Resolution
Chengcheng Wang, Zhiwei Hao, Yehui Tang +4
Diffusion-based super-resolution (SR) models have recently garnered significant attention due to their potent restoration capabilities. But conventional diffusion models perform no…
A Survey on Transformer Compression
Yehui Tang, Yunhe Wang, Jianyuan Guo +4
Transformer plays a vital role in the realms of natural language processing (NLP) and computer vision (CV), specially for constructing large language models (LLM) and large vision…
PanGu-: Enhancing Language Model Architectures via Nonlinearity Compensation
Yunhe Wang, Hanting Chen, Yehui Tang +17
The recent trend of large language models (LLMs) is to increase the scale of both model size (\aka the number of parameters) and dataset to achieve better generative ability, which…
One-for-All: Bridge the Gap Between Heterogeneous Architectures in Knowledge Distillation
Zhiwei Hao, Jianyuan Guo, Kai Han +4
Knowledge distillation~(KD) has proven to be a highly effective approach for enhancing model performance through a teacher-student training scheme. However, most existing distillat…
Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanism
Chengcheng Wang, Wei He, Ying Nie +4
In the past years, YOLO-series models have emerged as the leading approaches in the area of real-time object detection. Many studies pushed up the baseline to a higher level by mod…
ParameterNet: Parameters Are All You Need
Kai Han, Yunhe Wang, Jianyuan Guo +1
The large-scale visual pretraining has significantly improve the performance of large vision models. However, we observe the \emph{low FLOPs pitfall} that the existing low-FLOPs mo…
VanillaKD: Revisit the Power of Vanilla Knowledge Distillation from Small Scale to Large Scale
Zhiwei Hao, Jianyuan Guo, Kai Han +3
The tremendous success of large models trained on extensive datasets demonstrates that scale is a key ingredient in achieving superior results. Therefore, the reflection on the rat…
VanillaNet: the Power of Minimalism in Deep Learning
Hanting Chen, Yunhe Wang, Jianyuan Guo +1
At the heart of foundation models is the philosophy of "more is different", exemplified by the astonishing success in computer vision and natural language processing. However, the…