13 papers
Enhancing Multimodal RLVR with Pairwise Token Contrast and Adaptive Trajectory Confidence
Yiran Zhang, Hanbo Huang, Jielan Li +3
Reinforcement learning with verifiable rewards (RLVR) improves multimodal reasoning, but group-relative policy optimization broadcasts a single sequence-level advantage to every to…
REACT: Physically and Chemically Consistent Reconstruction of Marine Active Tracers
Wenbin Dai, Hao Zheng, Shiyu Liang +6
Reconstructing global sea surface pH from sparse observations is critical for monitoring ocean acidification and understanding marine carbon cycling. Traditional assimilation and i…
Contract Memory Compiler: Resolve, Then Traverse
Zhi Song, XiMing Xing, Chunhan Li +9
External memory lets language-model agents answer questions about histories too long for the answer model's context window. Updates create a harder problem than retrieving a recent…
PertMind: Eliciting Emergent Biological Reasoning in LLM via Reinforcement Learning on Cellular Perturbation Data
Zhenchao Tang, Xiaogang Xu, Tianxu Lv +16
Large language models can describe mechanisms, yet scalable post-training still depends on costly, manually curated biological reasoning traces. Here we show that cellular perturba…
Branch-JEPA: Finite-Support Predictive Distributions for JEPA World Models
Zhi Song, Ximing Xing, Zhenchao Tang +9
Joint-embedding predictive architectures (JEPAs) learn dynamics by predicting future observations in representation space. Yet most JEPA world models return one latent successor, e…
GGBound: A Genome-Grounded Agent for Microbial Life-Boundary Prediction
Hanbo Huang, Xuan Gong, Jing Wang +4
Characterizing the physiological life boundaries of microbial strains, including viable temperature, pH, salinity, substrate utilization, and morphology, is central to biotechnolog…
Reflection Anchors for Propagation-Aware Visual Retention in Long-Chain Multimodal Reasoning
Xuan Gong, Hanbo Huang, Hao Zheng +4
Long chain-of-thought (CoT) reasoning improves large vision--language models, but visual information often fades during generation, limiting long-horizon multimodal reasoning. Exis…
Resource-Constrained UAV-Based Weed Detection for Site-Specific Management on Edge Devices
Linyuan Wang, Haibo Yao, Te-Ming Tseng +4
Weeds compete with crops for light, water, and nutrients, reducing yield and crop quality. Efficient weed detection is essential for site-specific weed management (SSWM). Although…
RLSpoofer: A Lightweight Evaluator for LLM Watermark Spoofing Resilience
Hanbo Huang, Xuan Gong, Yiran Zhang +2
Large language model (LLM) watermarking has emerged as a promising approach for detecting and attributing AI-generated text, yet its robustness to black-box spoofing remains insuff…
VCORE: Variance-Controlled Optimization-based Reweighting for Chain-of-Thought Supervision
Xuan Gong, Senmiao Wang, Hanbo Huang +2
Supervised fine-tuning (SFT) on long chain-of-thought (CoT) trajectories has emerged as a crucial technique for enhancing the reasoning abilities of large language models (LLMs). H…
RLCracker: Evaluating the Worst-Case Vulnerability of LLM Watermarks with Adaptive RL Attacks
Hanbo Huang, Yiran Zhang, Hao Zheng +5
Large language model (LLM) watermarking has shown promise in detecting AI-generated content and mitigating misuse, with prior work claiming robustness against paraphrasing and text…
From Parameters to Prompts: Understanding and Mitigating the Factuality Gap between Fine-Tuned LLMs
Xuan Gong, Hanbo Huang, Shiyu Liang
Factual knowledge extraction aims to explicitly extract knowledge parameterized in pre-trained language models for application in downstream tasks. While prior work has been invest…
A Middle Path for On-Premises LLM Deployment: Preserving Privacy Without Sacrificing Model Confidentiality
Hanbo Huang, Yihan Li, Bowen Jiang +5
Privacy-sensitive users require deploying large language models (LLMs) within their own infrastructure (on-premises) to safeguard private data and enable customization. However, vu…