PPL
Hao Fang
Papers (8)
Reasoning Matters: Mitigate Hallucination in Multimodal Large Reasoning Models via Reasoning-Conditioned Preference OptimizationHarmony in Diversity: Multi-domain Contrastive Policy Optimization for Large Reasoning ModelsPrompt2Fingerprint: Plug-and-Play LLM Fingerprinting via Text-to-Weight GenerationSustainable Intelligence for the Wild: Democratizing Ecological Monitoring via Knowledge-Adaptive Edge Expert AgentsGenerative Long-term User Interest Modeling for Click-Through Rate PredictionMistletoe: Stealthy Acceleration-Collapse Attacks on Speculative DecodingDo Joint Audio-Video Generation Models Understand Physics?Beyond Negative Rollouts: Positive-Only Policy Optimization with Implicit Negative Gradients