AI.info

Bo Zheng

Explore Bo Zheng on AI.info.

• Re$^3$Cap: Retrieval-Guided Refinement for Image Captioning Enhancement via Reinforcement Learning
• MAC: A Conversion Rate Prediction Benchmark Featuring Labels Under Multiple Attribution Mechanisms
• Stop Unnecessary Reflection: Training LRMs for Efficient Reasoning with Adaptive Reflection and Length Coordinated Penalty
• Expert Divergence Learning for MoE-based Language Models
• CoMeT: Collaborative Memory Transformer for Efficient Long Context Modeling
• COMI: Coarse-to-fine Context Compression via Marginal Information Gain
• Modeling Cascaded Delay Feedback for Online Net Conversion Rate Prediction: Benchmark, Insights and Solutions
• The Flexibility Trap: Rethinking the Value of Arbitrary Order in Diffusion Language Models
• Towards Interactive Intelligence for Digital Humans
• UniLS: End-to-End Audio-Driven Avatars for Unified Listening and Speaking
• ViT$^3$: Unlocking Test-Time Training in Vision
• Thinking with Drafts: Speculative Temporal Reasoning for Efficient Long Video Understanding
• ConceptGuard: Proactive Safety in Text-and-Image-to-Video Generation through Multimodal Risk Detection
• MOON2.0: Dynamic Modality-balanced Multimodal Representation Learning for E-commerce Product Understanding
• Enabling Agents to Communicate Entirely in Latent Space
• VC4VG: Optimizing Video Captions for Text-to-Video Generation
• Bid2X: Revealing Dynamics of Bidding Environment in Online Advertising from A Foundation Model Lens
• Identity-Preserving Image-to-Video Generation via Reward-Guided Optimization
• Attention Illuminates LLM Reasoning: The Preplan-and-Anchor Rhythm Enables Fine-Grained Policy Optimization
• MeSH: Memory-as-State-Highways for Recursive Transformers