5 citations · 5 across the 19 of their papers we have counts for
21 papers
Style Over Substance: Content-Invariant Wrappers Flip LLM Safety-Judge Verdicts
Yongxi Zhou, Wenbo Ye, Yuanzhe Liu +3
Automatic safety judges -- for example Llama Guard, or GPT-4o given a grading prompt -- produce the numbers behind reported jailbreak success rates, defense evaluations, and safety…
Single Canonical Prompts Underestimate LLM Safety's Surface-Form Sensitivity
Yongxi Zhou, Junwei Yao, Yuanzhe Liu +4
A benchmark score is a measurement instrument, yet most benchmarks read each item at a single canonical surface form. We ask whether that reading is faithful: when an item's intent…
Hybrid-Policy Self-Editing for Composable Unstructured Knowledge Editing
Tianci Liu, Zihan Dong, Tianchun Li +8
Large language models (LLMs) achieve remarkable performance across natural language tasks, yet they are trained on static corpora and their knowledge quickly becomes outdated in a…
Personalization as Inverse Planning: Learning Latent Design Intents for Agentic Slide Generation via Structural Denoising
Tianci Liu, Zihan Dong, Linjun Zhang +5
Slide design requires personalizing both deck themes and page layouts. Yet, current AI agent-based methods struggle with fine-grained, page-level design. Solely relying on prespeci…
How Benchmarks Mis-Score Computer-Use Agents
Zihan Dong, Zhiyuan Ma, Zekun Wang +5
Computer-use agents (CUA) are being deployed to browse the web and operate desktop software, yet their benchmark scores are still commonly produced by brittle scripted oracles. A s…
RIMS: Preference Optimization via Smoothed Multi-pair Aggregation for Small-Scale LLM Retrieval-Augmented Generation
Pei Tian, Zihan Dong, Tianci Liu +2
Small-scale language models (SLMs) are attractive for retrieval-augmented generation (RAG) in resource-constrained settings, but their limited capacity makes them highly sensitive…
Decompose Sparsely Where You Should, Absorb Densely Where You Should No
Ruixuan Deng, Zehao Jin, Zekun Wang +1
Sparse autoencoders (SAEs) are typically trained to reconstruct the \textbf{entire} residual stream through a sparse dictionary, implicitly assuming that all activation content is…
Evidence Over Plans: Online Trajectory Verification for Skill Distillation
Yang Zhou, Zihan Dong, Zhenting Wang +7
Agent skills can remarkably improve task success rates by using human-written procedural documents, but their quality is difficult to assess without environment-grounded verificati…
RUBRIC-ARROW: Alternating Pointwise Rubric Reward Modeling for LLM Post-training in Non-verifiable Domains
Haoxiang Jiang, Zihan Dong, Tianci Liu +5
Pointwise reward modeling offers critical signals for LLM post-training, yet struggles with absolute scoring in subjective, non-verifiable settings. Rubric-based methods address th…
AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration
Jiaqi Liu, Shi Qiu, Mairui Li +33
Automating scientific discovery requires more than generating papers from ideas. Real research is iterative: hypotheses are challenged from multiple perspectives, experiments fail…
Self-Consolidating Language Models: Continual Knowledge Incorporation from Context
Zekun Wang, Anant Gupta, Zihan Dong +1
Large language models (LLMs) increasingly receive information as streams of passages, conversations, and long-context workflows. While longer context windows expose more evidence,…
DARE: Difficulty-Adaptive Reinforcement Learning with Co-Evolved Difficulty Estimation
Yang Zhou, Can Jin, Zihan Dong +7
Reinforcement learning improves the reasoning ability of large language models but remains costly and sample-inefficient, as many rollouts provide weak learning signals. Difficulty…
Alternating Reinforcement Learning for Rubric-Based Reward Modeling in Non-Verifiable LLM Post-Training
Ran Xu, Tianci Liu, Zihan Dong +6
Standard reward models typically predict scalar scores that fail to capture the multifaceted nature of response quality in non-verifiable domains, such as creative writing or open-…
LUCID-SAE: Learning Unified Vision-Language Sparse Codes for Interpretable Concept Discovery
Difei Gu, Yunhe Gao, Gerasimos Chatzoudis +6
Sparse autoencoders (SAEs) offer a natural path toward comparable explanations across different representation spaces. However, current SAEs are trained per modality, producing dic…
Evaluating LLMs When They Do Not Know the Answer: Statistical Evaluation of Mathematical Reasoning via Comparative Signals
Zihan Dong, Zhixian Zhang, Yang Zhou +3
Evaluating mathematical reasoning in LLMs is constrained by limited benchmark sizes and inherent model stochasticity, yielding high-variance accuracy estimates and unstable ranking…
AceSearcher: Bootstrapping Reasoning and Search for LLMs via Reinforced Self-Play
Ran Xu, Yuchen Zhuang, Zihan Dong +7
Search-augmented LLMs often struggle with complex reasoning tasks due to ineffective multi-hop retrieval and limited reasoning ability. We propose AceSearcher, a cooperative self-p…
Contrastive Network Representation Learning
Zihan Dong, Xin Zhou, Ryumei Nakada +2
Network representation learning seeks to embed networks into a low-dimensional space while preserving the structural and semantic properties, thereby facilitating downstream tasks…
Avoid Catastrophic Forgetting with Rank-1 Fisher from Diffusion Models
Zekun Wang, Anant Gupta, Zihan Dong +1
Catastrophic forgetting remains a central obstacle for continual learning in neural models. Popular approaches -- replay and elastic weight consolidation (EWC) -- have limitations:…
AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
Can Jin, Yang Zhou, Qixin Zhang +8
Test-time scaling strategies for Large Language Models predominantly rely on either reinforcement learning with sparse outcome rewards or search-based methods guided by static Proc…
Mitigating Heterogeneous Token Overfitting in LLM Knowledge Editing
Tianci Liu, Ruirui Li, Zihan Dong +6
Large language models (LLMs) have achieved remarkable performance on various natural language tasks. However, they are trained on static corpora and their knowledge can become outd…
Students' Perceptions and Preferences of Generative Artificial Intelligence Feedback for Programming
Zhengdong Zhang, Zihan Dong, Yang Shi +3
The rapid evolution of artificial intelligence (AI), specifically large language models (LLMs), has opened opportunities for various educational applications. This paper explored t…