Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model
Paper • 2607.24904 • Published • 38
森さくら
davidtorres7
AI & ML interests
Alignment-focused model research. Mostly focused on experiments.
Recent Activity
liked a model 4 days ago
Qwen/Qwen2.5-7B-Instruct liked a model 4 days ago
meta-llama/Llama-3.1-8B-Instruct liked a model 4 days ago
deepseek-ai/DeepSeek-R1Organizations
None yet
upvoted a paper about 1 month ago
upvoted a paper 3 months ago
upvoted 5
papers 4 months ago
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players
Paper • 2605.28816 • Published • 434
Geo-Align: Video Generation Alignment via Metric Geometry Reward
Paper • 2605.23903 • Published • 10
OSCAR: Offline Spectral Covariance-Aware Rotation for 2-bit KV Cache Quantization
Paper • 2605.17757 • Published • 66
Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining
Paper • 2605.14747 • Published • 149
LiVeAction: a Lightweight, Versatile, and Asymmetric Neural Codec Design for Real-time Operation
Paper • 2605.06628 • Published • 6
upvoted 4
papers 5 months ago
LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model
Paper • 2604.20796 • Published • 244
GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning
Paper • 2604.02721 • Published • 641
Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering
Paper • 2604.08224 • Published • 53
Do World Action Models Generalize Better than VLAs? A Robustness Study
Paper • 2603.22078 • Published • 9