7 papers
CHAIN: Calibrated LLM Forecasting via Causal-Temporal Hypergraph Inference
Wenjin Liu, Chenxi Wang, Yue Lu +2
Large language models have achieved significant progress in event forecasting, yet their probability outputs exhibit systematic calibration bias that varies heterogeneously across…
TIEM: Temporal Integration of Hypergraph Evidence and Skill Memory for Event-Driven Financial Forecasting
Wenjin Liu, Shen Pang, Chenxi Wang +6
Event-driven catalyst-outcome forecasting increasingly uses retrieval- and memory-augmented large language model agents for prediction. However, training-data contamination and tem…
CataOPD: Catalytic On-Policy Distillation for Large Language Model Reasoning
Wenjin Liu, Chenxi Wang, Jiapu Wang +3
Reinforcement learning (RL) and on-policy distillation (OPD) are two representative paradigms for improving large language model reasoning. However, when no correct trajectory is s…
AdaPilot: Towards Scene-Adaptive Policy Learning for Cross-Generator Text-to-Image Quality Optimization
Wenjin Liu, Fayuan Ke, Yue Lu +3
Existing methods for improving text-to-image generation quality have progressed from generator fine-tuning and prompt optimization to reinforcement learning with multi-turn visual…
MMDynOpt-Agent: Dynamic Optimization for Multimodal Large Language Model Reasoning via Reinforcement Learning
Wenjin Liu, Haoran Luo, Fayuan Ke +5
Recently, multimodal large language models (MLLMs) have demonstrated strong potential in visual understanding and complex reasoning tasks. However, existing methods often struggle…
Focus on What Matters: Fisher-Guided Adaptive Multimodal Fusion for Vulnerability Detection
Yun Bian, Yi Chen, HaiQuan Wang +2
Software vulnerability detection can be formulated as a binary classification problem that determines whether a given code snippet contains security defects. Existing multimodal me…
GovRelBench:A Benchmark for Government Domain Relevance
Haiquan Wang, Yi Chen, Shang Zeng +2
Current evaluations of LLMs in the government domain primarily focus on safety considerations in specific scenarios, while the assessment of the models' own core capabilities, part…