13 citations · 29 across the 31 of their papers we have counts for
32 papers
Audio-Zero: Label-Free Self-Evolution for Fine-Grained Audio Reasoning
Siqian Tong, Xuan Li, Chaozhuo Li +5
Large Audio Language models (LALMs) have made rapid progress on acoustic understanding, yet they still struggle with fine-grained audio reasoning (e.g., recognizing event order, re…
Multimodal Reward Hacking in Reinforcement Learning
Jiayu Yao, Yiwei Wang, Anmeng Zhang +5
Reinforcement learning (RL) is increasingly used to align multimodal large language models (MLLMs), but higher rewards do not always imply better task performance. This risk is amp…
Lost in a Single Vector: Improving Long-Document Retrieval with Chunk Evidence Aggregation
Shanshan Lyu, Yiwei Wang, Yujun Cai +2
Dense retrieval ranks one query vector against one document vector. On long documents, this interface can fail when a short but decisive span is weakened during document encoding b…
SAW: Stage-Aware Dynamic Weighting for Multi-Objective Reinforcement Learning in Large Language Models
Yuchen He, Baolong Bi, Shenghua Liu +7
Although multi-objective reinforcement learning (MORL) is central to aligning large language models with complex human preferences, the prevailing practice of static weighted summa…
Readable Yet Unpredictable: Rotated-Outcome Prediction in Vision-Language Models
Lexin Wang, Shenghua Liu, Yiwei Wang +2
Can vision-language models predict what a 180° rotation would reveal from the original image alone? We study this ability through Rotated-Outcome Prediction: given an original imag…
HighlightBench: Benchmarking Markup-Driven Table Reasoning in Scientific Documents
Lexin Wang, Shenghua Liu, Yiwei Wang +5
Visual markups such as highlights, underlines, and bold text are common in table-centric documents. Although multimodal large language models (MLLMs) have made substantial progress…
PRISM-: Differential Subspace Steering for Prompt Highlighting in Large Language Models
Yuyao Ge, Shenghua Liu, Yiwei Wang +5
Prompt highlighting steers a large language model to prioritize user-specified text spans during generation. A key challenge of existing Key-editing approaches is extracting steeri…
PromptCD: Test-Time Behavior Enhancement via Polarity-Prompt Contrastive Decoding
Baolong Bi, Yuyao Ge, Shenghua Liu +9
Reliable AI systems require large language models (LLMs) to exhibit behaviors aligned with human preferences and values. However, most existing alignment approaches operate at trai…
AuTAgent: A Reinforcement Learning Framework for Tool-Augmented Audio Reasoning
Siqian Tong, Xuan Li, Yiwei Wang +5
Large Audio Language Models (LALMs) excel at perception but struggle with complex reasoning requiring precise acoustic measurements. While external tools can extract fine-grained f…
Gated Differentiable Working Memory for Long-Context Language Modeling
Lingrui Mei, Shenghua Liu, Yiwei Wang +7
Long contexts challenge transformers: attention scores dilute across thousands of tokens, critical information is often lost in the middle, and models struggle to adapt to novel pa…
Reward and Guidance through Rubrics: Promoting Exploration to Improve Multi-Domain Reasoning
Baolong Bi, Shenghua Liu, Yiwei Wang +6
Recent advances in reinforcement learning (RL) have significantly improved the complex reasoning capabilities of large language models (LLMs). Despite these successes, existing met…
Not in Sync: Unveiling Temporal Bias in Audio Chat Models
Jiayu Yao, Shenghua Liu, Yiwei Wang +5
Large Audio Language Models (LALMs) are increasingly applied to audio understanding and multimodal reasoning, yet their ability to locate when events occur remains underexplored. W…
Beyond Black-Box Interventions: Latent Probing for Faithful Retrieval-Augmented Generation
Linfeng Gao, Qinggang Zhang, Baolong Bi +9
Retrieval-Augmented Generation (RAG) systems often fail to maintain contextual faithfulness, generating responses that conflict with the provided context or fail to fully leverage…
A Survey of Vibe Coding with Large Language Models
Yuyao Ge, Lingrui Mei, Zenghao Duan +12
The advancement of large language models (LLMs) has catalyzed a paradigm shift from code generation assistance to autonomous coding agents, enabling a novel development methodology…
Focusing by Contrastive Attention: Enhancing VLMs' Visual Reasoning
Yuyao Ge, Shenghua Liu, Yiwei Wang +6
Vision-Language Models (VLMs) have demonstrated remarkable success across diverse visual tasks, yet their performance degrades in complex visual environments. While existing enhanc…
A Survey of Context Engineering for Large Language Models
Lingrui Mei, Jiayu Yao, Yuyao Ge +12
The performance of Large Language Models (LLMs) is fundamentally determined by the contextual information provided during inference. This survey introduces Context Engineering, a f…
RefineX: Learning to Refine Pre-training Data at Scale from Expert-Guided Programs
Baolong Bi, Shenghua Liu, Xingzhang Ren +7
The foundational capabilities of large language models (LLMs) are deeply influenced by the quality of their pre-training corpora. However, enhancing data quality at scale remains a…
Rethinking All Evidence: Enhancing Trustworthy Retrieval-Augmented Generation via Conflict-Driven Summarization
Juan Chen, Baolong Bi, Wei Zhang +5
Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by integrating their parametric knowledge with external retrieved content. However, knowledge conflicts c…
Who is in the Spotlight: The Hidden Bias Undermining Multimodal Retrieval-Augmented Generation
Jiayu Yao, Shenghua Liu, Yiwei Wang +5
Multimodal Retrieval-Augmented Generation (RAG) systems have become essential in knowledge-intensive and open-domain tasks. As retrieval complexity increases, ensuring the robustne…
a1: Steep Test-time Scaling Law via Environment Augmented Generation
Lingrui Mei, Shenghua Liu, Yiwei Wang +5
Large Language Models (LLMs) have made remarkable breakthroughs in reasoning, yet continue to struggle with hallucinations, logical errors, and inability to self-correct during com…
Innate Reasoning is Not Enough: In-Context Learning Enhances Reasoning Large Language Models with Less Overthinking
Yuyao Ge, Shenghua Liu, Yiwei Wang +4
Recent advances in Large Language Models (LLMs) have introduced Reasoning Large Language Models (RLLMs), which employ extended thinking processes with reflection and self-correctio…
Parameters vs. Context: Fine-Grained Control of Knowledge Reliance in Language Models
Baolong Bi, Shenghua Liu, Yiwei Wang +4
Retrieval-Augmented Generation (RAG) mitigates hallucinations in Large Language Models (LLMs) by integrating external knowledge. However, conflicts between parametric knowledge and…
Context-DPO: Aligning Language Models for Context-Faithfulness
Baolong Bi, Shaohan Huang, Yiwei Wang +11
Reliable responses from large language models (LLMs) require adherence to user instructions and retrieved information. While alignment techniques help LLMs align with human intenti…
HiddenGuard: Fine-Grained Safe Generation with Specialized Representation Router
Lingrui Mei, Shenghua Liu, Yiwei Wang +3
As Large Language Models (LLMs) grow increasingly powerful, ensuring their safety and alignment with human values remains a critical challenge. Ideally, LLMs should provide informa…