We have 7 of 53 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.
Context Language Models are introduced, language models that natively manage their own context and can be steered with natural-language instructions evolved through a standard skill-optimization loop, improving held-out accuracy by up to 35.9 points on a context-management task while reducing compute.
This work defines the scaling inflection point as the per-session budget where marginal Elo gains match the independent-sampling reference, and proposes Elo-per-token analysis, which tracks the best solution found at each token budget and uses a Bradley-Terry model to aggregate within-task orderings into Elo ratings ac...
This work addresses the adverse interactions between sparsity and data repetition, and presents evidence for the core mechanisms of overfitting and its potential remediation, and suggests promising avenues for future methods to reduce over-specialization in model parameters by disrupting memorization patterns.
SPADE (Self-Play in Adaptive Synthetic Executable Executable Environments), a self-play RL framework in which a single LLM plays two roles: an Environment Designer that writes complete, long-horizon training environments as executable code with an OpenAI Gym-style reset()/step() interface, and a Reasoning Agent that le...
Switch Distillation is proposed, a simple mid-training objective that distills on tokens where the teacher is confident, using teacher predictive entropy as a lightweight routing signal, and otherwise falls back to cross-entropy, which consistently outperforms existing distillation objectives across teacher sizes.
Prefix Sliding is proposed, which discards tokens during reasoning that are not part of the prefix or the window of the last few thousand tokens, allowing for efficient long-horizon test-time scaling.
SPADE (Self-Play in Adaptive Synthetic Executable Executable Environments), a self-play RL framework in which a single LLM plays two roles: an Environment Designer that writes complete, long-horizon training environments as executable code with an OpenAI Gym-style reset()/step() interface, and a Reasoning Agent that le...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
