4 citations · 9 across the 45 of their papers we have counts for
15 papers · 1 filter
SearchSkill: Teaching LLMs to Use Search Tools with Evolving Skill Banks
Jinchao Hu, Meizhi Zhong, Kehai Chen +1
Teaching language models to use search tools is not only a question of whether they search, but also of whether they issue good queries. This is especially important in open-domain…
Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey
Bingzheng Qu, Kehai Chen, Xuefeng Bai +1
Recent progress in multimodal large language models (MLLMs) is reshaping video translation from a cascaded pipeline of automatic speech recognition, machine translation, text-to-sp…
Tailoring Teaching to Aptitude: Direction-Adaptive Self-Distillation for LLM Reasoning
Hongbin Zhang, Chaozheng Wang, Kehai Chen +4
On-policy self-distillation (OPSD) is an emerging LLM post-training paradigm in which the model serves as its own teacher: conditioned on privileged information such as a reference…
MemReread: Enhancing Agentic Long-Context Reasoning via Memory-Guided Rereading
Baibei Ji, Xiaoyang Weng, Juntao Li +3
Long-context reasoning tasks have motivated agent-memory approaches that process document chunks sequentially while maintaining a dynamically updated memory, avoiding the quadratic…
Through the Lens of Character: Resolving Modality-Role Interference in Multimodal Role-Playing Agent
Yihong Tang, Kehai Chen, Xuefeng Bai +1
The advancement of Multimodal Large Language Models (MLLMs) has expanded Role-Playing Agents (RPAs) into visually grounded environments. However, human vision is inherently subject…
Mitigating Multimodal Hallucination via Phase-wise Self-reward
Yu Zhang, Chuyang Sun, Kehai Chen +3
Large Vision-Language Models (LVLMs) still struggle with vision hallucination, where generated responses are inconsistent with the visual input. Existing methods either rely on lar…
Mathematical Reasoning Enhanced LLM for Formula Derivation: A Case Study on Fiber NLI Modellin
Yao Zhang, Yuchen Song, Xiao Luo +4
Recent advances in large language models (LLMs) have demonstrated strong capabilities in code generation and text synthesis, yet their potential for symbolic physical reasoning in…
Mitigating Translationese Bias in Multilingual LLM-as-a-Judge via Disentangled Information Bottleneck
Hongbin Zhang, Kehai Chen, Xuefen Bai +4
Large language models (LLMs) have become a standard for multilingual evaluation, yet they exhibit a severe systematic translationese bias. In this paper, translationese bias is cha…
Beyond Token-Level Policy Gradients for Complex Reasoning with Large Language Models
Mufan Xu, Kehai Chen, Xuefeng Bai +4
Existing policy-gradient methods for auto-regressive language models typically select subsequent tokens one at a time as actions in the policy. While effective for many generation…
Beyond Unimodal Shortcuts: MLLMs as Cross-Modal Reasoners for Grounded Named Entity Recognition
Jinlong Ma, Yu Zhang, Xuefeng Bai +5
Grounded Multimodal Named Entity Recognition (GMNER) aims to extract text-based entities, assign them semantic categories, and ground them to corresponding visual regions. In this…
Dynamics Within Latent Chain-of-Thought: An Empirical Study of Causal Structure
Zirui Li, Xuefeng Bai, Kehai Chen +4
Latent or continuous chain-of-thought methods replace explicit textual rationales with a number of internal latent steps, but these intermediate computations are difficult to evalu…
Instruction Anchor: Dissecting the Mechanistic Dynamics of Modality Arbitration
Yu Zhang, Mufan Xu, Xuefeng Bai +4
Modality following is the ability to selectively leverage multimodal contexts based on user instructions. It is fundamental to the safety and reliability of multimodal large langua…
Decoupling Skeleton and Flesh: Efficient Multimodal Table Reasoning with Disentangled Alignment and Structure-aware Guidance
Yingjie Zhu, Xuefeng Bai, Kehai Chen +4
Reasoning over table images remains challenging for Large Vision-Language Models (LVLMs) due to complex layouts and tightly coupled structure-content information. Existing solution…
Character-R1: Enhancing Role-Aware Reasoning in Role-Playing Agents via RLVR
Yihong Tang, Kehai Chen, Xuefeng Bai +4
Current role-playing agents (RPAs) are typically constructed by imitating surface-level behaviors, but this approach lacks internal cognitive consistency, often causing out-of-char…
Beyond Rigid: Benchmarking Non-Rigid Video Editing
Bingzheng Qu, Xuefeng Bai, Kehai Chen +1
As video generation models are increasingly expected to manipulate physical dynamics, there is a growing need to move evaluation beyond appearance fidelity and semantic alignment.…