1 citations · 1 across the 22 of their papers we have counts for
23 papers
Woodpecker Distillation: Weak Models Diagnose Reasoning Bugs in Strong Models
Dayu Wang, Jiaye Yang, Weikang Li +4
Large language models often fail on reasoning tasks despite possessing the capability to solve them. We argue that many such failures arise from localized reasoning bugs in interme…
Learning User-Aware Recall: Personalized Retrieval in Long-Term Conversational Memory
ZhiShu Jiang, Haibo Liu, Xin Shen +6
Long-term conversational agents are expected to remember past interactions, but memory is useful only when the right evidence is recalled for the right user. Existing memory-augmen…
It Takes 8 Tokens: Weak-to-Strong Off-Policy RL via Auxiliary Branches
Dayu Wang, Jiaye Yang, Weikang Li +4
Reinforcement learning with verifiable rewards has emerged as a standard approach for enhancing reasoning in large language models, which typically optimizes the policy by contrast…
Break the Brake, Not the Wheel: Untargeted Jailbreak via Entropy Maximization
Mengqi He, Xinyu Tian, Xin Shen +6
Recent studies show that gradient-based universal image jailbreaks on vision-language models (VLMs) exhibit little or no cross-model transferability, casting doubt on the feasibili…
RepoZero: Can LLMs Generate a Code Repository from Scratch?
Zhaoxi Zhang, Yiming Xu, Jiahui Liang +7
Large Language Models (LLMs) have recently shown remarkable progress in code generation, yet their ability to construct complete software repositories from scratch remains poorly u…
ActTraitBench: Quantifying the Knowledge-Decision Gap in Large Language Models via Human-Grounded Behavioral Validation
Yutong Yang, Chenxi Miao, Weikang Li +1
While Large Language Models (LLMs) can convincingly simulate personas in explicit self-reports, they often deviate in implicit behavioral decisions, revealing a substantial Knowled…
Trait-Aware Policy Optimization for Autoregressive Multi-Trait Essay Scoring
Zhengyang Wang, Sanwoo Lee, Jiaxin Wang +3
Multi-trait essay scoring aims to provide fine-grained evaluation of writing quality across multiple dimensions. However, how to effectively post-train autoregressive scoring model…
InjectFlow: Weak Guides Strong via Orthogonal Injection for Flow Matching
Dayu Wang, Jiaye Yang, Weikang Li +2
Flow Matching (FM) has recently emerged as a leading approach for high-fidelity visual generation, offering a robust continuous-time alternative to ordinary differential equation (…
DuCCAE: A Hybrid Engine for Immersive Conversation via Collaboration, Augmentation, and Evolution
Xin Shen, Zhishu Jiang, Jiaye Yang +13
Immersive conversational systems in production face a persistent trade-off between responsiveness and long-horizon task capability. Real-time interaction is achievable for lightwei…
LM-Lexicon: Improving Definition Modeling via Harmonizing Semantic Experts
Yang Liu, Jiaye Yang, Weikang Li +3
We introduce LM-Lexicon, an innovative definition modeling approach that incorporates data clustering, semantic expert learning, and model merging using a sparse mixture-of-experts…
Beyond Alignment: Expanding Reasoning Capacity via Manifold-Reshaping Policy Optimization
Dayu Wang, Jiaye Yang, Weikang Li +2
Reinforcement Learning with Verifiable Rewards (RLVR) has demonstrated remarkable success in enhancing the reasoning capabilities of Large Language Models (LLMs). However, recent s…
Stay in Character, Stay Safe: Dual-Cycle Adversarial Self-Evolution for Safety Role-Playing Agents
Mingyang Liao, Yichen Wan, shuchen wu +6
LLM-based role-playing has rapidly improved in fidelity, yet stronger adherence to persona constraints commonly increases vulnerability to jailbreak attacks, especially for risky o…
Video-MSR: Benchmarking Multi-hop Spatial Reasoning Capabilities of MLLMs
Rui Zhu, Xin Shen, Shuchen Wu +6
Spatial reasoning has emerged as a critical capability for Multimodal Large Language Models (MLLMs), drawing increasing attention and rapid advancement. However, existing benchmark…
Decide Then Retrieve: A Training-Free Framework with Uncertainty-Guided Triggering and Dual-Path Retrieval
Wang Chen, Guanqiang Qi, Weikang Li +3
Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating external knowledge, but existing approaches indiscriminately trigger retrieval and rely…
Student Guides Teacher: Weak-to-Strong Inference via Spectral Orthogonal Exploration
Dayu Wang, Jiaye Yang, Weikang Li +4
Large Language Models (LLMs) often suffer from ''Reasoning Collapse'' on challenging mathematical reasoning tasks, where stochastic sampling produces lexical variations of the same…
One Tool Is Enough: Reinforcement Learning for Repository-Level LLM Agents
Zhaoxi Zhang, Yitong Duan, Yanzhi Zhang +9
Locating files and functions requiring modification in large software repositories is challenging due to their scale and structural complexity. Existing LLM-based methods typically…
FingerCap: Fine-grained Finger-level Hand Motion Captioning
Xin Shen, Rui Zhu, Lei Shen +10
Understanding fine-grained human hand motion is fundamental to visual perception, embodied intelligence, and multimodal communication. In this work, we propose Fine-grained Finger-…
SciEGQA: A Dataset for Scientific Evidence-Grounded Question Answering and Reasoning
Wenhan Yu, Zhaoxi Zhang, Wang Chen +5
Scientific documents contain complex multimodal structures, which makes evidence localization and scientific reasoning in Document Visual Question Answering particularly challengin…
Probabilistic Modeling of Intentions in Socially Intelligent LLM Agents
Feifan Xia, Yuyang Fang, Defang Li +5
We present a probabilistic intent modeling framework for large language model (LLM) agents in multi-turn social dialogue. The framework maintains a belief distribution over a partn…
CMRAG: Co-modality-based visual document retrieval and question answering
Wang Chen, Wenhan Yu, Guanqiang Qi +5
Retrieval-Augmented Generation (RAG) has become a core paradigm in document question answering tasks. However, existing methods have limitations when dealing with multimodal docume…
Cross-LoRA: A Data-Free LoRA Transfer Framework across Heterogeneous LLMs
Feifan Xia, Mingyang Liao, Yuyang Fang +6
Traditional parameter-efficient fine-tuning (PEFT) methods such as LoRA are tightly coupled with the base model architecture, which constrains their applicability across heterogene…
PAIRS: Parametric-Verified Adaptive Information Retrieval and Selection for Efficient RAG
Wang Chen, Guanqiang Qi, Weikang Li +3
Retrieval-Augmented Generation (RAG) has become a cornerstone technique for enhancing large language models (LLMs) with external knowledge. However, current RAG systems face two cr…
Reducing Cognitive Overhead in Tool Use via Multi-Small-Agent Reinforcement Learning
Dayu Wang, Yutong Liu, Jiaye Yang +3
Recent advances in multi-agent systems highlight the potential of specialized small agents that collaborate via division of labor. Existing tool-integrated reasoning systems, howev…