Logit-Entropy Adaptive Stopping Heuristic for Efficient Chain-of-Thought Reasoning
Paper • 2511.04654 • Published
👋 Open to Work
Atif Quamar
atifquamar07
AI & ML interests
reasoning in language models, reinforcement learning, ai safety
Recent Activity
authored a paper 27 days ago
Logit-Entropy Adaptive Stopping Heuristic for Efficient Chain-of-Thought Reasoning authored a paper 27 days ago
Adaptive Blockwise Search: Inference-Time Alignment for Large Language Models authored a paper 27 days ago
Prefix-Denoising Consistency: Test-Time Verification for Diffusion Language ModelsOrganizations
authored 7
papers 27 days ago
Adaptive Blockwise Search: Inference-Time Alignment for Large Language Models
Paper • 2510.23334 • Published
Prefix-Denoising Consistency: Test-Time Verification for Diffusion Language Models
Paper • 2608.25311 • Published
Self-Adapting Group of Experts for Multi-Agent Reasoning
Paper • 2609.35412 • Published
Privileged Solutions or Context-Induced Teacher Behavior? Dissecting On-Policy Self-Distillation
Paper • 2608.09228 • Published
Learning Modal-Mixed Chain-of-Thought Reasoning with Latent Embeddings
Paper • 2602.00574 • Published
Reliable Chain-of-Thought via Prefix Consistency
Paper • 2605.07654 • Published • 1
updated a
model 6 months ago
published a
model 6 months ago
updated 4
models over 1 year ago
published 3
models over 1 year ago
updated a
model over 1 year ago
published a
model over 1 year ago
updated a
model over 1 year ago
published a
model over 1 year ago