6 citations · 40 across the 46 of their papers we have counts for
10 papers · 1 filter
PhysEvo: Astra Can Act, Let It
Wenqing Tian, Zeyu Zhang, Zhaocheng Liu +3
Astra can act, yet reliable manipulation depends on the system through which it observes and controls the world. We introduce PhysEvo, a framework for physical recursive self-impro…
EviSD: Evidence-Conditioned Self-Distillation for Search-Augmented Agents
Jianan Xie, Xin Sun, Zhongqi Chen +4
Outcome-based reinforcement learning enables search-augmented language agents to learn from verifiable final answers, but its trajectory-level credit cannot distinguish the contrib…
CRANE: Knowledge Editing for Reasoning MLLMs
Han Huang, Hao Wang, Mengqi Zhang +3
The emergence of reasoning multimodal large language models (MLLMs), which generate explicit chain-of-thought (CoT) reasoning before producing answers, has introduced a new challen…
Learning When Not to Act: Mitigating Tool Abuse in Agentic Reinforcement Learning
Liuji Chen, Dianxing Tang, Xing Shi +4
Agentic reinforcement learning can induce tool abuse, where models overuse external tools even for queries solvable by internal reasoning. Existing approaches mitigate this issue w…
From Profiles to Steering Vectors: Global Sparse Priors and Local Semantic Calibration for Personalized Text Generation
Liuji Chen, Zeyu Zhang, Xinyuan Zhang +4
Personalized text generation requires models to capture user-specific writing styles from historical data. Existing approaches based on retrieval, parameter-efficient fine-tuning,…
MultiBind: A Benchmark for Attribute Misbinding in Multi-Subject Generation
Wenqing Tian, Hanyi Mao, Zhaocheng Liu +4
Subject-driven image generation is increasingly expected to support fine-grained control over multiple entities within a single image. In multi-reference workflows, users may provi…
Chatting with Images for Introspective Visual Thinking
Junfei Wu, Jian Guan, Qiang Liu +4
Current large vision-language models (LVLMs) typically rely on text-only reasoning based on a single-pass visual encoding, which often leads to loss of fine-grained visual informat…
NAG: A Unified Native Architecture for Encoder-free Text-Graph Modeling in Language Models
Haisong Gong, Zhibo Liu, Qiang Liu +2
Prevailing methods for integrating graphs into Language Models (LMs) typically rely on a segregated architecture: external Graph Neural Networks (GNNs) encode structural topology,…
ToolWeaver: Weaving Collaborative Semantics for Scalable Tool Use in Large Language Models
Bowen Fang, Wen Ye, Yunyue Su +8
Prevalent retrieval-based tool-use pipelines struggle with a dual semantic challenge: their retrievers often employ encoders that fail to capture complex semantics, while the Large…
Predict the Retrieval! Test time adaptation for Retrieval Augmented Generation
Xin Sun, Zhongqi Chen, Qiang Liu +5
Retrieval-Augmented Generation (RAG) has emerged as a powerful approach for enhancing large language models' question-answering capabilities through the integration of external kno…