AI.info
Hao Wang
Explore Hao Wang on AI.info.
- STAR : Sentence Translation Alignment Rate for Document-to-Document Machine Translation
- AsymSpec: Context-Asymmetric Speculative Decoding for Agentic LLMs
- Twins: Learn to Predict Unified Representations with Focal Loss
- Reward Modeling for Multi-Agent Orchestration
- OmniGAIA: Towards Native Omni-Modal AI Agents
- ProactiveMobile: A Comprehensive Benchmark for Boosting Proactive Intelligence on Mobile Devices
- RuleSmith: Multi-Agent LLMs for Automated Game Balancing
- AriadneMem: Threading the Maze of Lifelong Memory for LLM Agents
- Reliable and Responsible Foundation Models: A Comprehensive Survey
- MAS-ProVe: Understanding the Process Verification of Multi-Agent Systems
- Kimi K2.5: Visual Agentic Intelligence
- Rethinking the Flow-Based Gradual Domain Adaptation: A Semi-Dual Optimal Transport Perspective
- ShotFinder: Imagination-Driven Open-Domain Video Shot Retrieval via Web Search
- FOREVER: Forgetting Curve-Inspired Memory Replay for Language Model Continual Learning
- SimRPD: Optimizing Recruitment Proactive Dialogue Agents through Simulator-Based Data Evaluation and Selection
- RoboArmGS: High-Quality Robotic Arm Splatting via Bézier Curve Refinement
- DDTime: Dataset Distillation with Spectral Alignment and Information Bottleneck for Time-Series Forecasting
- Center-Outward q-Dominance: A Sample-Computable Proxy for Strong Stochastic Dominance in Multi-Objective Optimisation
- SSR: Socratic Self-Refine for Large Language Model Reasoning
- Perceptual Quality Assessment of 3D Gaussian Splatting: A Subjective Dataset and Prediction Metric
- DAMBench: A Multi-Modal Benchmark for Deep Learning-based Atmospheric Data Assimilation
- World Simulation with Video Foundation Models for Physical AI
- DistDF: Time-Series Forecasting Needs Joint-Distribution Wasserstein Alignment
- Quadratic Direct Forecast for Training Multi-Step Time-Series Forecast Models
- DeepAgent: A General Reasoning Agent with Scalable Toolsets
- Moving Light Adaptive Colonoscopy Reconstruction via Illumination-Attenuation-Aware 3D Gaussian Splatting
- Chronos-2: From Univariate to Universal Forecasting
- $M^2PO$: Multi-Perspective Multi-Pair Preference Optimization for Machine Translation
- The Stackelberg Speaker: Optimizing Persuasive Communication in Social Deduction Games