Knowledge-Geometry Decoupling: Refreshable Pretrained Transfer for Streaming Recommendation
Paper • 2608.02738 • Published • 38
🔄 In a Training Loop
Milton Montiel
miltmont
·
AI & ML interests
Reinforcement learning
Recent Activity
upvoted a paper about 9 hours ago
Knowledge-Geometry Decoupling: Refreshable Pretrained Transfer for Streaming Recommendation upvoted a paper about 9 hours ago
AURORA-LM: Autoencoding Unified Representation for Continuous-Latent Diffusion Language Modeling upvoted a paper about 9 hours ago
JoyAI-Video-Edit: Real-Time Open-Ended Video Editing with Autoregressive DiffusionOrganizations
None yet
upvoted 3
papers about 9 hours ago
upvoted 4
papers 1 day ago
DiffusionGemma Technical Report
Paper • 2608.00146 • Published • 31
DAPD: Dual-Anchored Policy Distillation
Paper • 2608.01735 • Published • 89
LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks
Paper • 2608.01964 • Published • 144
Progressive Agent Skill Generation via Reinforcement Learning
Paper • 2608.01678 • Published • 56
upvoted a paper 2 days ago
upvoted 3
papers 3 days ago
N_0-VTLA: Scaling Vision-Tactile-Language-Action Model with Latent Tactile Tokens
Paper • 2607.23782 • Published • 61
Meshy T2: Fast Native Mesh Generation with Flow Matching
Paper • 2607.28675 • Published • 53
From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement
Paper • 2607.23802 • Published • 97
upvoted a paper 4 days ago
upvoted 3
papers 6 days ago
SkillRise: Agentic Reinforcement Learning for Cross-Task Skill Evolution
Paper • 2607.26784 • Published • 28
HumanCLAW: Can Vision-Language Models Act Through a Body?
Paper • 2607.27180 • Published • 76
TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM
Paper • 2607.27205 • Published • 139
upvoted 2
papers 7 days ago
upvoted an article 7 days ago
Article
The Engineering Handbook for GRPO + LoRA with Verl: Training Qwen2.5 on Multi-GPU
Weyaxi
• • 24 upvoted 2
papers 9 days ago