AI.info
Jian Yang
Explore Jian Yang on AI.info.
- ArtSociety: Multi-Agent Multimodal Collaboration for Art Emotion Understanding
- Representation Handoffs for OpenArm-Based Laboratory Mobile Manipulation
- RoMeRL: Balancing Feedback Coverage and the Memory-Reward Trap in Self-Evolving Agent Memory via Reduced-Order Utility States
- LUVE : Latent-Cascaded Ultra-High-Resolution Video Generation with Dual Frequency Experts
- Towards Fair and Comprehensive Evaluation of Routers in Collaborative LLM Systems
- BiasScope: Towards Automated Detection of Bias in LLM-as-a-Judge Evaluation
- WorldTravel: A Realistic Multimodal Travel-Planning Benchmark with Tightly Coupled Constraints
- Dynamics Within Latent Chain-of-Thought: An Empirical Study of Causal Structure
- Large-Scale Terminal Agentic Trajectory Generation from Dockerized Environments
- Federated Learning at the Forefront of Fairness: A Multifaceted Perspective
- NSR-Boost: A Neuro-Symbolic Residual Boosting Framework for Industrial Legacy Models
- HumanLLM: Benchmarking and Improving LLM Anthropomorphism via Human Cognitive Patterns
- Small but Mighty: Dynamic Wavelet Expert-Guided Fine-Tuning of Large-Scale Models for Optical Remote Sensing Object Segmentation
- Rethinking Table Pruning in TableQA: From Sequential Revisions to Gold Trajectory-Supervised Parallel Search
- MorphAny3D: Unleashing the Power of Structured Latent in 3D Morphing
- Geometry-to-Image Synthesis-Driven Generative Point Cloud Registration
- FUSER: Feed-Forward MUltiview 3D Registration Transformer and SE(3)$^N$ Diffusion Refinement
- DiP: Taming Diffusion Models in Pixel Space
- From Parameter to Representation: A Closed-Form Approach for Controllable Model Merging
- MVU-Eval: Towards Multi-Video Understanding Evaluation for Multimodal LLMs
- FreeControl: Efficient, Training-Free Structural Control via One-Step Attention Extraction
- Restore Text First, Enhance Image Later: Two-Stage Scene Text Image Super-Resolution with Glyph Structure Guidance
- Controllable-LPMoE: Adapting to Challenging Object Segmentation via Dynamic Local Priors from Mixture-of-Experts
- UltraHR-100K: Enhancing UHR Image Synthesis with A Large-Scale High-Quality Dataset