Picture for Bo Wang

Bo Wang

Tencent, WeChat Pay

Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspective

Add code
Dec 18, 2024
Viaarxiv icon

EvoWiki: Evaluating LLMs on Evolving Knowledge

Add code
Dec 18, 2024
Viaarxiv icon

AIR-Bench: Automated Heterogeneous Information Retrieval Benchmark

Add code
Dec 17, 2024
Viaarxiv icon

Text-Video Multi-Grained Integration for Video Moment Montage

Add code
Dec 12, 2024
Viaarxiv icon

Semantic Scene Completion Based 3D Traversability Estimation for Off-Road Terrains

Add code
Dec 11, 2024
Viaarxiv icon

jina-clip-v2: Multilingual Multimodal Embeddings for Text and Images

Add code
Dec 11, 2024
Viaarxiv icon

Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling

Add code
Dec 06, 2024
Viaarxiv icon

Enhancing Instruction-Following Capability of Visual-Language Models by Reducing Image Redundancy

Add code
Nov 23, 2024
Figure 1 for Enhancing Instruction-Following Capability of Visual-Language Models by Reducing Image Redundancy
Figure 2 for Enhancing Instruction-Following Capability of Visual-Language Models by Reducing Image Redundancy
Figure 3 for Enhancing Instruction-Following Capability of Visual-Language Models by Reducing Image Redundancy
Figure 4 for Enhancing Instruction-Following Capability of Visual-Language Models by Reducing Image Redundancy
Viaarxiv icon

Gazing at Rewards: Eye Movements as a Lens into Human and AI Decision-Making in Hybrid Visual Foraging

Add code
Nov 14, 2024
Figure 1 for Gazing at Rewards: Eye Movements as a Lens into Human and AI Decision-Making in Hybrid Visual Foraging
Figure 2 for Gazing at Rewards: Eye Movements as a Lens into Human and AI Decision-Making in Hybrid Visual Foraging
Figure 3 for Gazing at Rewards: Eye Movements as a Lens into Human and AI Decision-Making in Hybrid Visual Foraging
Figure 4 for Gazing at Rewards: Eye Movements as a Lens into Human and AI Decision-Making in Hybrid Visual Foraging
Viaarxiv icon

Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent

Add code
Nov 05, 2024
Figure 1 for Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent
Figure 2 for Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent
Figure 3 for Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent
Figure 4 for Hunyuan-Large: An Open-Source MoE Model with 52 Billion Activated Parameters by Tencent
Viaarxiv icon