We have 5 of 7 papers
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
How much can test-time computation improve a language model, and at what cost? Test-time scaling is widely proposed as a substitute for larger models, but existing comparisons mostly evaluate one domain at a time and rarely charge selection to the budget. We introduce SELF-POT, a benchmark and evaluation framework that...
Scaling reasoning typically spends more compute on reinforcement learning (RL) or on inference. We show that a completed RL training history can yield policies stronger than the checkpoints visited by its optimizer. We call this policy-space scaling: expanding the deployable policy set accessible from a fixed RL histor...
Sampling multiple solutions spends computation on intermediate deductions and unfinished arguments as well as final answers. We introduce ReSolve, a training-free inference procedure that reuses this candidate reasoning through selective generative moderation. An answer-distribution controller invokes a model to examin...
This work is the first to unveil the critical role of the null space and harness it for model optimization, and uses a simplified analytical model about optimization to demonstrate why null-space can effectively reduce attention entropy, thereby improving the efficiency of reasoning.
This work introduces Constraint-First Reasoning (CFR), a training-free two-stage prompting protocol that improves direct CoT on multiple backbones and positions CFR as a targeted test-time intervention whose benefit depends on recoverable constraints and reliable Stage 1 extraction.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
