Watch Before You Answer: Learning from Visually Grounded Post-Training
Paper • 2604.05117 • Published • 162
Olivier Macdonald
omacdonald52
AI & ML interests
None yet
Recent Activity
upvoted a paper 5 days ago
Watch Before You Answer: Learning from Visually Grounded Post-Training upvoted a paper 23 days ago
Dream-RSI: Recursive Self-Improvement through Evolving Worlds liked a model 25 days ago
urukbdhero/granite4.1-3b-ecommerceOrganizations
None yet
upvoted a paper 5 days ago
upvoted a paper 23 days ago
upvoted a paper 29 days ago
upvoted 3
papers about 1 month ago
Aspire: Can Models Self-Evolve from Vague Goals?
Paper • 2608.31111 • Published • 274
Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models
Paper • 2608.25518 • Published • 60
WarpSAC: Towards the Pinnacle of Scalable Off-policy RL by Rethinking Exploration and Exploitation
Paper • 2608.24479 • Published • 139
upvoted 3
papers about 2 months ago
Spark-to-Paper: End-to-End Research Paper Generation as a Composable Skill
Paper • 2608.11924 • Published • 111
On-Policy Self-Distillation without Any Supervision
Paper • 2608.06296 • Published • 181
Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA
Paper • 2608.09819 • Published • 181
upvoted 3
papers 2 months ago
TARS: Timestep-Aware Data Scaling for 3D-Free Video Re-Shooting
Paper • 2607.28261 • Published • 18
DistillAlign: Coordinating Mode Covering and Mode Seeking in Autoregressive Video Distillation
Paper • 2607.26811 • Published • 18
HiFi-UMI: Learning Deployable Manipulation Policies from High-Fidelity UMI Data Alone
Paper • 2607.25895 • Published • 95