16 papers
VLA-: Learning Physical State Transition for Vision-Language-Action Models
Qi Lu, Jiarun Li, Ce Zhang +5
Vision-language-action (VLA) models transfer semantic knowledge acquired through vision-language pretraining to robot control, achieving strong performance across various benchmark…
Spatial-Interactor: Learning Spatial Reasoning through Interaction with the Observable Physical World
Kaixiang Yao, Xu Wang, Miao Pan +10
Spatial reasoning is essential for vision-language models (VLMs) to understand and act in the physical world. Reasoning in dynamic environments requires VLMs to perceive local stat…
Dual-Axis Policy Optimization for LLM Agents: Bayesian Feedback Attribution and Trajectory Mass Normalization
Yingxuan Zhuang, Binhe Yu, Jingxiao Yang +6
Reinforcement learning for LLM agents involves two distinct optimization di- mensions: how environment feedback is exploited within a trajectory, and how complete trajectories are…
Reconciling Process Supervision with Outcome-Based Credit in Agentic Policy Optimization
Jingxiao Yang, Wangjie Gan, Yingxuan Zhuang +3
Outcome-based reinforcement learning provides verified feedback for language-model agents, but assigns trajectory-level advantage uniformly to all decisions, yielding coarse credit…
Embodied-Navigator: Point, Think, Memorize, and Align for Efficient Navigation
Hongyan Feng, Sunlai Chen, Xuanyu Liu +9
Although Large Vision-Language Models (VLMs) have significantly advanced embodied navigation, their direct deployment remains challenging, as existing methods often force VLMs into…
AttriMem: Attribution-Guided Process Feedback for Agent Memory Construction
Qinfeng Li, Yuntai Bao, Xinyan Yu +7
Effective memory is crucial for LLM agents, yet constructing it effectively remains challenging. A memory-construction policy decides what information to extract, store, update, co…
SkillAligner: Treating Retrieved Skills as Adaptable Drafts at Execution Time
Qinfeng Li, Dalin He, Yuntai Bao +7
General-purpose skills promise reusable procedural knowledge for language agents, yet semantic relevance does not guarantee execution utility: a retrieved skill may encode assumpti…
Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text
Xu Wang, Kaixiang Yao, Miao Pan +4
Spatial intelligence is essential for agents to move from static semantic understanding toward interacting with the physical world. Many spatial tasks are grounded in continuous vi…
VLA-Corrector: Lightweight Detect-and-Correct Inference for Adaptive Action Horizon
Yi Pan, Miao Pan, Qi Lu +8
Vision-Language-Action (VLA) foundation models have recently achieved strong progress in embodied intelligence. To reduce policy-call frequency while preserving temporal coherence,…
Towards Steering without Sacrifice: Principled Training of Steering Vectors for Prompt-only Interventions
Yuntai Bao, Qinfeng Li, Xinyan Yu +6
Recently, steering vectors (SVs) have emerged as an effective and lightweight approach to steer behaviors of large language models (LLMs), among which fine-tuned SVs are more effec…
PragLocker: Protecting Agent Intellectual Property in Untrusted Deployments via Non-Portable Prompts
Qinfeng Li, Yuntai Bao, Jianghui Hu +5
LLM agents rely on prompts to implement task-specific capabilities based on foundation LLMs, making agent prompts valuable intellectual property. However, in untrusted deployments,…
SARE: Sample-wise Adaptive Reasoning for Training-free Fine-grained Visual Recognition
Jingxiao Yang, DaLin He, Miao Pan +7
Recent advances in Large Vision-Language Models (LVLMs) have enabled training-free Fine-Grained Visual Recognition (FGVR). However, effectively exploiting LVLMs for FGVR remains ch…
SCHK-HTC: Sibling Contrastive Learning with Hierarchical Knowledge-Aware Prompt Tuning for Hierarchical Text Classification
Ke Xiong, Qian Wu, Wangjie Gan +2
Few-shot Hierarchical Text Classification (few-shot HTC) is a challenging task that involves mapping texts to a predefined tree-structured label hierarchy under data-scarce conditi…
Faithful Bi-Directional Model Steering via Distribution Matching and Distributed Interchange Interventions
Yuntai Bao, Xuhong Zhang, Jintao Chen +7
Intervention-based model steering offers a lightweight and interpretable alternative to prompting and fine-tuning. However, by adapting strong optimization objectives from fine-tun…
Do Not Merge My Model! Safeguarding Open-Source LLMs Against Unauthorized Model Merging
Qinfeng Li, Miao Pan, Jintao Chen +5
Model merging has emerged as an efficient technique for expanding large language models (LLMs) by integrating specialized expert models. However, it also introduces a new threat: m…
RAGFort: Dual-Path Defense Against Proprietary Knowledge Base Extraction in Retrieval-Augmented Generation
Qinfeng Li, Miao Pan, Ke Xiong +6
Retrieval-Augmented Generation (RAG) systems deployed over proprietary knowledge bases face growing threats from reconstruction attacks that aggregate model responses to replicate…