2 citations · 8 across the 30 of their papers we have counts for
41 papers
Where Should a Stuck Agent Spend Its Next Tokens? Causal Attribution of Inference-Time Resources
Saiyue Lyu, Jerrold Huang, Yunbei Zhang +4
Inference-time scaling is often treated as a token-budget problem, but a failed coding agent can seek qualitatively different resources: computation, information, or feedback. We i…
Simple Agentic Memory for Generalist Robot Policies
Yuyou Zhang, Yunbei Zhang, Miao Li +4
Visual-memory systems commonly retain or compress past observations. Robot control additionally requires interaction-derived state that no individual frame may explicitly represent…
How Medical VLMs Underutilize Their Vision Encoders: A Dermatology Perspective
Janet Wang, Yunbei Zhang, Xiao Wang +1
Medical Vision-Language Models (VLMs) show significant promise for clinical image understanding, offering accurate diagnosis with interpretable reasoning. However, a critical perfo…
LIBERO-MAX: Do Robot Policies Adapt When the World Changes?
Yunbei Zhang, Zijian Jin, Yuanzhe Liu +14
Robots must often continue a task after a target moves, the viewpoint shifts, or an obstacle appears, even though their earlier observations and committed actions reflect the previ…
A Survey on Self-Improving Test-Time Intelligence: Feedback-Driven Adapting, Learning, and Scaling at Inference
Shuaicheng Niu, Guohao Chen, Yaofo Chen +14
The ability of AI systems to improve their behavior during deployment is becoming increasingly important. As inference moves beyond the static execution of a fixed trained model, a…
Dynamic Hub-and-Spoke Memory for Streaming Video Understanding
Xinru Jiang, Lin Zhao, Xi Xiao +7
Streaming video understanding requires answering questions at arbitrary times over a continuously growing visual stream. The central challenge is to compactly remember long-range h…
Towards Continual Test-Time Adaptation of Vision-Language Models in Open-Vocabulary Semantic Segmentation
Chandler Timm C. Doloriel, Yunbei Zhang, Sarthak Kumar Maharana +5
Open-vocabulary semantic segmentation (OVSS) relies on vision-language alignment to recognize arbitrary text-defined categories, yet this alignment is fragile under continual test-…
Continual Test-Time Adaptation via Entropy Sensitivity-Guidance in Strict Online Setting
Chandler Timm C. Doloriel, Yunbei Zhang, Muhammad Salman Siddiqui +4
Test-time adaptation (TTA) promises robustness under distribution shift by updating a pretrained model on unlabeled test data, but strict online TTA with batch size one and no acce…
Continual Test-Time Adaptation in Computer Vision: Methods, Benchmarks, and Future Directions
Sarthak Kumar Maharana, Shambhavi Mishra, Yunbei Zhang +6
Deep neural nets achieve remarkable performance when training and test data share the same distribution, but this assumption frequently breaks in real-world deployment, where data…
Adapting Vision Foundation Models with Cascaded Semantics
Xi Xiao, Xingjian Li, Cheng Han +8
Prompt tuning, a leading parameter-efficient adaptation paradigm in NLP, has recently been extended to computer vision. Visual prompt tuning (VPT) adapts pre-trained vision transfo…
Rethinking Layer-Wise Information Allocation for Vision Foundation Model Adaptation
Yuqi Li, Xi Xiao, Yunbei Zhang +6
Vision foundation models are increasingly reused as frozen backbones for downstream visual recognition, making parameter-efficient adaptation a central problem. Prompt-based adapta…
Less Tokens, Better Forecasts: Sparse Residual Routing for Efficient Weather Prediction
Janet Wang, Yunbei Zhang, Lin Zhao +3
Existing ViT-based weather forecasting models apply uniform computation across all spatial tokens, even though nearby atmospheric grid points often contain similar values and large…
Structure-Regularized Interpretable TCR-Epitope Prediction
Jiarui Li, Zixiang Yin, Yunbei Zhang +4
T cell receptor (TCR)-epitope binding prediction is essential for understanding adaptive immunity and developing immunotherapies. Existing sequence- and structure-based models ofte…
Staying VIGILant: Mitigating Visual Laziness via Counterfactual Visual Alignment in MLLMs
Xi Xiao, Chen Liu, Chih-Ting Liao +9
Multimodal large language models (MLLMs) extend large language models (LLMs) with visual perception, enabling joint reasoning over images and text. Despite inheriting strong reason…
Layer-Specific Prompt Fusion Discovery via Differentiable Search in Vision Foundation Models
Xi Xiao, Xingjian Li, Yunbei Zhang +7
Visual prompt tuning has emerged as a parameter-efficient fine-tuning approach for adapting large-scale Vision Transformers (ViTs) to downstream tasks. As its learnable prompts are…
One Skill, Two Masters: Serving Users and Attackers through Skill Injection
Haochang Hao, Dehai Min, Zhifang Zhang +5
Large language model agents use skills that package reusable instructions, code, and resources. Existing skill-injection attacks exploit trust in these packages by adding malicious…
EVA-0: Test-Time Model Evolution with Only Two Forward Passes per Sample
Guohao Chen, Shuaicheng Niu, Geng Li +4
Test-time model evolution offers a promising way for deployed models to improve from unlabeled test-time experience, yet most existing methods depend on backpropagation (BP), which…
Stop Comparing LLM Agents Without Disclosing the Harness
Yunbei Zhang, Janet Wang, Yingqiang Ge +3
This position paper argues that, for long-horizon tasks evaluated across models with comparable frontier capability, the agent execution harness, namely the infrastructure layer th…
Not All Directions Matter: Towards Structured and Task-Aware Low-Rank Model Adaptation
Xi Xiao, Chenrui Ma, Yunbei Zhang +7
Low-Rank Adaptation (LoRA) has become a cornerstone of parameter-efficient fine-tuning (PEFT). Yet, its efficacy is hampered by two fundamental limitations: semantic drift, by trea…
Adapting in the Dark: Efficient and Stable Test-Time Adaptation for Black-Box Models
Yunbei Zhang, Shuaicheng Niu, Chengyi Cai +2
Test-Time Adaptation (TTA) for black-box models accessible only via APIs remains a largely unexplored challenge. Existing approaches such as post-hoc output refinement offer limite…
ClawSafety: "Safe" LLMs, Unsafe Agents
Bowen Wei, Yunbei Zhang, Jinhao Pan +5
Personal AI agents like OpenClaw run with elevated privileges on users' local machines, where a single successful prompt injection can leak credentials, redirect financial transact…
Prime Once, then Reprogram Locally: An Efficient Alternative to Black-Box Service Model Adaptation
Yunbei Zhang, Chengyi Cai, Feng Liu +1
Adapting closed-box service models (i.e., APIs) for target tasks typically relies on reprogramming via Zeroth-Order Optimization (ZOO). However, this standard strategy is known for…
Wan-R1: Verifiable-Reinforcement Learning for Video Reasoning
Ming Liu, Yunbei Zhang, Shilong Liu +2
Video generation models produce visually coherent content but struggle with tasks requiring spatial reasoning and multi-step planning. Reinforcement learning (RL) offers a path to…
Seeing Clearly, Reasoning Confidently: Plug-and-Play Remedies for Vision Language Model Blindness
Xin Hu, Haomiao Ni, Yunbei Zhang +3
Vision language models (VLMs) have achieved remarkable success in broad visual understanding, yet they remain challenged by object-centric reasoning on rare objects due to the scar…