6 citations · 6 across the 35 of their papers we have counts for
25 papers · 1 filter
StartLux-Decision: AutoThink Decision Models with Reinforcement Learning for Calibrated Deliberative Decisions
Xialie Zhuang, Zunhai Su, Jia Pan +3
We introduce StartLux-Decision, decision models from 0.8B to 27B parameters that combine efficient single-pass prediction with adaptive, confidence-guided reasoning. The Instant mo…
Before the Arrest: Benchmarking LLMs on Criminal Profiling from Incomplete Evidence
Yutong Yao, Yanjie Cao, Guanhua Chen +5
Large Language Models (LLMs) are increasingly applied to legal and criminal justice tasks, yet existing work focuses almost exclusively on post-arrest scenarios where the suspect's…
JustMem: Just-Enough Memory Access for Long-Term Conversations
Guanhua Chen, Yanting Wang, Wenjing Zhi +1
Efficient long-term conversational memory requires retrieving sufficient evidence without indiscriminately expanding the context presented to the language model. This is challengin…
ROAM: Robust Organization of Atomic Memories for Agents through Semantic Relations
Jianjie Zheng, Peng Lai, Sijie Cheng +3
Long-term language-model agents rely on external memory across interactions. Atomic memories are particularly useful: their fine-grained semantic boundaries enable precise retrieva…
UniRRM: Unified Reasoning Reward Models Across Languages and Evaluation Paradigms
Peng Lai, Yichao Du, Junchao Wu +6
Reinforcement learning (RL) excels on tasks with verifiable rewards, but in open-ended tasks, the reliability of reward models remains a key challenge. Existing solutions either de…
AlignDiff: Exploiting Model-Intrinsic Information for Better Preference Data Selection
Peng Lai, He Zhu, Zhiwen Ruan +6
Aligning large language models with human preferences remains a challenge, primarily due to the critical role of preference data quality in effective alignment. Existing datasets a…
Making Clinical Language Models Auditable: Concept-Guided Fine-Tuning for Robust Prediction
Jin Mu, Guanhua Chen
Clinical language models can achieve strong in-hospital accuracy yet fail under deployment shifts because they exploit note-specific artifacts (e.g., templates, separators, boilerp…
Beyond Static Rules: Automated Discovery of Latent Vulnerabilities in Text-to-SQL
Hanqing Wang, Yongdong Chi, Jian Yang +4
While Large Language Models (LLMs) have achieved remarkable success in Text-to-SQL tasks, their deployment in real-world environments is hindered by latent reliability issues. Iden…
StatABench: Dataset and Framework for Evaluating Statistical Analysis Capabilities of LLMs
Youxin Zhu, Yixuan Ding, Peng Lai +3
Statistical analysis is a broad, complex field requiring both domain knowledge and tool proficiency. While prior work has evaluated large language models (LLMs) in this domain, exi…
Bridging the Agent-World Gap: Text World Models for LLM-based Agents
Yixia Li, Hongru Wang, Peng Lai +13
Large language model (LLM)-based agents are increasingly used in interactive textual environments, from web navigation and code editing to tool use and long-horizon dialogue. Yet m…
CAPruner: Conceptual-Adjacent Scene Graph Pruner for Enhancing 3D Spatial Reasoning of Large Language Models
Shengli Zhou, Xiangchen Wang, Guanhua Chen +1
Large language models (LLMs) have recently been applied to 3D vision-language (3D-VL) tasks, which require spatial reasoning to identify target objects relative to anchors. Scene g…
From Scenes to Elements: Multi-Granularity Evidence Retrieval for Verifiable Multimodal RAG
Guanhua Chen, Chuyue Huang, Yutong Yao +4
Multimodal Retrieval-Augmented Generation (RAG) systems retrieve evidence at coarse granularities (entire images or scenes), creating a mismatch with fine-grained user queries and…
Chain-of-Procedure: Hierarchical Visual-Language Reasoning for Procedural QA
Guanhua Chen, Yutong Yao, Shenghe Sun +5
Recent advances in vision-language models (VLMs) have achieved impressive results on standard image-text tasks, yet their potential for visual procedure question answering (VP-QA)…
Learning Agentic Policy from Action Guidance
Yuxiang Ji, Zengbin Wang, Yong Wang +6
Agentic reinforcement learning (RL) for Large Language Models (LLMs) critically depends on the exploration capability of the base policy, as training signals emerge only within its…
Robust LLM Unlearning Against Relearning Attacks: The Minor Components in Representations Matter
Zeguan Xiao, Xuanzhe Xu, Yun Chen +5
Large language model (LLM) unlearning aims to remove specific data influences from pre-trained model without costly retraining, addressing privacy, copyright, and safety concerns.…
CulturALL: Benchmarking Multilingual and Multicultural Competence of LLMs on Grounded Tasks
Peiqin Lin, Chenyang Lyu, Wenjiang Luo +22
Large language models (LLMs) are now deployed worldwide, inspiring a surge of benchmarks that measure their multilingual and multicultural abilities. However, these benchmarks prio…
InstructDiff: Domain-Adaptive Data Selection via Differential Entropy for Efficient LLM Fine-Tuning
Junyou Su, He Zhu, Xiao Luo +6
Supervised fine-tuning (SFT) is fundamental to adapting large language models, yet training on complete datasets incurs prohibitive costs with diminishing returns. Existing data se…
Enhancing Large Language Model Reasoning via Selective Critical Token Fine-Tuning
Zhiwen Ruan, Yixia Li, He Zhu +4
Large language models (LLMs) primarily rely on supervised fine-tuning (SFT) as a key method to adapt pre-trained models to domain-specific tasks such as mathematical reasoning. How…
TAG-INSTRUCT: Controlled Instruction Complexity Enhancement through Structure-based Augmentation
He Zhu, Zhiwen Ruan, Junyou Su +4
High-quality instruction data is crucial for developing large language models (LLMs), yet existing approaches struggle to effectively control instruction complexity. We present TAG…
PlanGPT-VL: Enhancing Urban Planning with Domain-Specific Vision-Language Models
He Zhu, Junyou Su, Minxin Chen +4
In the field of urban planning, existing Vision-Language Models (VLMs) frequently fail to effectively analyze and evaluate planning maps, despite the critical importance of these v…
Towards Lightweight, Adaptive and Attribute-Aware Multi-Aspect Controllable Text Generation with Large Language Models
Chenyu Zhu, Yefeng Liu, Chenyang Lyu +5
Multi-aspect controllable text generation aims to control text generation in attributes from multiple aspects, making it a complex but powerful task in natural language processing.…
LayAlign: Enhancing Multilingual Reasoning in Large Language Models via Layer-Wise Adaptive Fusion and Alignment Strategy
Zhiwen Ruan, Yixia Li, He Zhu +5
Despite being pretrained on multilingual corpora, large language models (LLMs) exhibit suboptimal performance on low-resource languages. Recent approaches have leveraged multilingu…
FANNO: Augmenting High-Quality Instruction Data with Open-Sourced LLMs Only
He Zhu, Junyou Su, Tianle Lun +4
Instruction fine-tuning stands as a crucial advancement in leveraging large language models (LLMs) for enhanced task performance. However, the annotation of instruction datasets ha…
Unlocking Multi-View Insights in Knowledge-Dense Retrieval-Augmented Generation
Guanhua Chen, Wenhan Yu, Xiao Lu +3
While Retrieval-Augmented Generation (RAG) plays a crucial role in the application of Large Language Models (LLMs), existing retrieval methods in knowledge-dense domains like law a…