AI.info

Xin Wang

Explore Xin Wang on AI.info.

• Per-Matrix Optimality Is Not Enough: Three-Level Optimization for Low-Rank LLM Compression
• CoverPrune: Coverage-Driven Token Pruning for 3D VLMs via Optimal Transport
• AssetFormer: Modular 3D Assets Generation with Autoregressive Transformer
• MMDeepResearch-Bench: A Benchmark for Multimodal Deep Research Agents
• A Safety Report on GPT-5.2, Gemini 3 Pro, Qwen3-VL, Grok 4.1 Fast, Nano Banana Pro, and Seedream 4.5
• PALM-Bench: A Comprehensive Benchmark for Personalized Audio-Language Models
• Cross-platform Product Matching Based on Entity Alignment of Knowledge Graph with RAEA model
• BackdoorVLM: A Benchmark for Backdoor Attacks on Vision-Language Models
• V-ReasonBench: Toward Unified Reasoning Benchmark Suite for Video Generation Models
• The Impact of Quantization on Large Reasoning Model Reinforcement Learning
• SMART: A Surrogate Model for Predicting Application Runtime in Dragonfly Systems
• Dual Mamba for Node-Specific Representation Learning: Tackling Over-Smoothing with Selective State Space Modeling
• Rethinking Facial Expression Recognition in the Era of Multimodal Large Language Models: Benchmark, Datasets, and Beyond
• GraphChain: Large Language Models for Large-scale Graph Analysis via Tool Chaining
• Beyond Single Images: Retrieval Self-Augmented Unsupervised Camouflaged Object Detection
• GAPS: A Clinically Grounded, Automated Benchmark for Evaluating AI Clinicians