2 citations · 5 across the 20 of their papers we have counts for
21 papers
REWIND: Uncertainty-Guided Trajectory Repair for Test-Time Reasoning
Yi Ding, Mengyu Wang, Min Zhou +1
An early mistake in the generated reasoning can constrain all subsequent reasoning. Repeated-generation methods, like MCMC-based approaches, attempt to improve output quality by sa…
ConWriter: Transition-Constrained Stateful Long-Form Story Generation with Lightweight Neuro-Symbolic Consistency Control
Jindong Li, Yang Yang, Zihao Liu +2
Long-form story generation requires models to preserve narrative consistency across extended contexts, yet existing prompting-based methods often accumulate temporal, factual, char…
Learning to Look Again: Loss-Gap Supervision for Free-form Crop Routing in Vision-Language Models
Jinchang Zhu, Rong Fu, Yi Ding +3
Vision-language models (VLMs) fail many detail-centric questions for a concrete reason: the answer is visible in the image, yet lost after the image is compressed into a low-resolu…
Learning When Not to Listen: Selective Anti-Interference Pretraining for Language Models
Jinchang Zhu, Haowei He, Yi Ding +5
Language models can over-condition on irrelevant preceding text: predictions already supported by local context may still change when distant, unrelated prefix tokens are perturbed…
FCPRAG: Fusion-Controller Parametric Retrieval-Augmented Generation for Stable Multi-Passage LoRA Injection
Jinchang Zhu, Jindong Li, Yi Ding +5
Parametric retrieval-augmented generation (PRAG) injects retrieved evidence into a large language model (LLM) through passage-specific LoRA adapters, reducing reliance on long in-c…
SynWeaver: Website-Prior Task and Trajectory Co-Synthesis for Web Agents
Ruitao Wang, Yuwen Hao, Menglin Yang
Web agents often struggle to generalize to unseen websites because they lack website-specific supervision. Recent exploration-based data synthesis methods reduce manual annotation,…
StorySpark: Module-wise Evolutionary Search for Story Premise Generation
Yang Yang, Zining Zhong, Qian Cao +5
A story premise is the creative spark from which a full narrative can grow. Yet LLM-based story generation has mostly emphasized later-stage planning, controllability, coherence, a…
HyBIRD: Hyperbolic Bridge Retrieval and Diagnosis for Methodology Inspiration Retrieval
Yang Yang, Boyun Xu, Hao Fu +6
Methodology Inspiration Retrieval (MIR) asks a system to retrieve prior papers whose methods can inspire a new research proposal. Unlike general scientific retrieval, the central c…
CoSPlay: Cooperative Self-Play at Test-Time with Self-Generated Code and Unit Test
Zhangyi Hu, Chenhui Liu, Tian Huang +6
Recently, Reinforcement Learning with Verifiable Rewards (RLVR) and Test-Time Scaling (TTS) have advanced LLM code generation through executable verification. Yet Ground-Truth Unit…
Expand More, Shrink Less: Shaping Effective-Rank Dynamics for Dense Scaling in Recommendation
Guoming Li, Shangyu Zhang, Junwei Pan +7
Scaling recommendation models is a central challenge in recommender systems. Recently, RankMixer has emerged as an effective solution, operating on a unified token representation a…
Learning Less Is More: Premature Upper-Layer Attention Specialization Hurts Language Model Pretraining
Jinchang Zhu, Jindong Li, Yuwen Hao +3
A causal-decoder block is hierarchical: lower layers build the residual basis that upper layers attend over. We identify a failure mode in GPT pretraining: upper layers commit to s…
Where Does Long-Context Supervision Actually Go? Effective-Context Exposure Balancing
Jinchang Zhu, Jindong Li, Chengyu Zou +4
Long-context adaptation is often viewed as window scaling, but this misses a token-level supervision mismatch: in packed training with document masking, each target token's effecti…
SRTJ: Self-Evolving Rule-Driven Training-Free LLM Jailbreaking
Jindong Li, Ying Liu, Yali Fu +4
LLMs are increasingly equipped with safety alignment mechanisms, yet recent studies demonstrate that they remain vulnerable to jailbreaking attacks that elicit harmful behaviors wi…
HeLa-Mem: Hebbian Learning and Associative Memory for LLM Agents
Jinchang Zhu, Jindong Li, Cheng Zhang +2
Long-term memory is a critical challenge for Large Language Model agents, as fixed context windows cannot preserve coherence across extended interactions. Existing memory systems r…
TurboEvolve: Towards Fast and Robust LLM-Driven Program Evolution
Yang Yang, Zining Zhong, Jindong Li +5
LLM-driven program evolution can discover high-quality programs, but high API cost and run-to-run variance hinder reliable progress. We propose TurboEvolve, a multi-island evolutio…
Continuous Knowledge Metabolism: Generating Scientific Hypotheses from Evolving Literature
Jinkai Tao, Yubo Wang, Xiaoyu Liu +1
Identifying promising research directions in fast-moving subareas is one of the most cognitively expensive tasks in modern AI research. Existing LLM-driven scientific discovery sys…
HyperbolicRAG: Enhancing Retrieval-Augmented Generation with Hyperbolic Representations
Linxiao Cao, Ruitao Wang, Jindong Li +2
Retrieval-augmented generation (RAG) enables large language models (LLMs) to access external knowledge, helping mitigate hallucinations and enhance domain-specific expertise. Graph…
Implicit Reasoning in Large Language Models: A Comprehensive Survey
Jindong Li, Yali Fu, Li Fan +6
Large Language Models (LLMs) have demonstrated strong generalization across a wide range of tasks. Reasoning with LLMs is central to solving multi-step problems and complex decisio…
CLIP-Powered Domain Generalization and Domain Adaptation: A Comprehensive Survey
Jindong Li, Yongguang Li, Yali Fu +4
As machine learning evolves, domain generalization (DG) and domain adaptation (DA) have become crucial for improving model robustness across diverse environments. Contrastive Langu…
Beyond Retraining: Training-Free Unknown Class Filtering for Source-Free Open Set Domain Adaptation of Vision-Language Models
Yongguang Li, Jindong Li, Qi Wang +4
Vision-language models (VLMs) have gained widespread attention for their strong zero-shot capabilities across numerous downstream tasks. However, these models assume that each test…
Cogito, ergo sum: A Neurobiologically-Inspired Cognition-Memory-Growth System for Code Generation
Yanlong Li, Jindong Li, Qi Wang +3
Large language models based Multi Agent Systems (MAS) have demonstrated promising performance for enhancing the efficiency and accuracy of code generation tasks. However,most exist…