A Safe Action Is Not Enough: Feasible-Future Decoding for Vision-Language-Action Policies
Paper • 2610.05166 • Published • 4
Matthieu Zimmer
MatthieuZ
AI & ML interests
None yet
Recent Activity
authored a paper about 5 hours ago
A Safe Action Is Not Enough: Feasible-Future Decoding for Vision-Language-Action Policies upvoted a paper about 9 hours ago
A Safe Action Is Not Enough: Feasible-Future Decoding for Vision-Language-Action Policies authored a paper 5 days ago
Composable Decoding on the Probability Simplex: Theory and ImplementationOrganizations
authored a
paper about 5 hours ago
upvoted a paper about 9 hours ago
authored 4
papers 5 days ago
Composable Decoding on the Probability Simplex: Theory and Implementation
Paper • 2609.34992 • Published • 11
Does This Action Still Explain the Task? Reverse Scoring for Diffusion Language Model Agents
Paper • 2609.38536 • Published • 11
The Weakest Link: Distilling LLM Reasoning with Worst-Case Constrained Reinforcement Learning
Paper • 2610.00332 • Published • 10
Tail-Influence Sampling for CVaR Policy Evaluation
Paper • 2609.38096 • Published • 26
upvoted 5
papers 6 days ago
The Weakest Link: Distilling LLM Reasoning with Worst-Case Constrained Reinforcement Learning
Paper • 2610.00332 • Published • 10
Tail-Influence Sampling for CVaR Policy Evaluation
Paper • 2609.38096 • Published • 26
Composable Decoding on the Probability Simplex: Theory and Implementation
Paper • 2609.34992 • Published • 11
Does This Action Still Explain the Task? Reverse Scoring for Diffusion Language Model Agents
Paper • 2609.38536 • Published • 11
iSDFT: Information-Proximal Self-Distillation for Continual Learning in LLMs
Paper • 2609.24646 • Published • 9
authored 6
papers 7 days ago
The $\mathbf{Y}$-Combinator for LLMs: Solving Long-Context Rot with $λ$-Calculus
Paper • 2603.20105 • Published • 37
Scalable Power Sampling: Unlocking Efficient, Training-Free Reasoning for LLMs via Distribution Sharpening
Paper • 2601.21590 • Published • 14
Multi-Task GRPO: Reliable LLM Reasoning Across Tasks
Paper • 2602.05547 • Published • 14
Decoding as Optimisation on the Probability Simplex: From Top-K to Top-P (Nucleus) to Best-of-K Samplers
Paper • 2602.18292 • Published • 14
iSDFT: Information-Proximal Self-Distillation for Continual Learning in LLMs
Paper • 2609.24646 • Published • 9
Beam Search as Test-Time Self-Distillation via Counterfactual Contexts
Paper • 2609.37041 • Published • 8
upvoted a paper 7 days ago
AWQ 4bit
2
#2 opened 4 months ago
by MatthieuZ
upvoted a paper 4 months ago