News
AI, cybersecurity, machine learning, scraping & programming news.
76 results on this page · clear filters
What Should World Models Forget? Stratified Retention for Continual Adaptation
Stationary targets versus drifting environments Continual learning has long treated performance loss on previously observed data as a signal of failure. This convention originates from prediction settings where a correct label rem...
RNADyn: A Benchmark for Generating and Understanding RNA Dynamics
RNA conformational dynamics and the limitations of static structures RNA molecules adopt multiple three-dimensional shapes to perform cellular tasks. These conformational changes are not captured by static structures obtained from...
LESSER: Post-Training Data Selection with Output-Layer Gradients
Why Post-Training Data Selection Matters for LLM Adaptation The choice of post-training data substantially affects large language model downstream performance. This makes data curation a high-leverage activity for teams that fine-...
Pivot-SD: Efficient Self-Distillation for Masked Diffusion Language Models
Masked diffusion language models (dLMs) present a parallel alternative to autoregressive models for complex reasoning, yet they encounter a credit-assignment problem: a few commitments during denoising sharply reduce uncertainty o...
Embedding Prediction Helps Image Generation
LLMs are increasingly applied to cybersecurity workflows, where they are expected to translate analysts' intent into tool invocations. However, existing evaluations focus on knowledge-based assessments or end-to-end agentic tasks,...
Cost-augmented Schrödinger bridges on graphs are exactly solvable: a Feynman-Kac tilt replaces learned control
The generalized Schrödinger bridge on a graph moves mass between two distributions while charging a cost for the states visited. Previous work has approached this by learning the rates of a controlled continuous-time Markov chain...
Decoding Looped Transformers Better for (Almost) Free
Looped Transformers achieve parameter efficiency by repeatedly executing a shared block across recurrent loops. Each loop yields an intermediate representation decodable for the same next token, yet standard decoding discards earl...
SoftServe: A Scalable Quasi-Newton Method for Deep Learning
Quasi-Newton methods have long been among the most effective approaches for large-scale unconstrained convex optimization, yet two obstacles have limited their adoption in deep learning: non-convexity and enormous parameter sizes....
From Gradients to Capabilities: Understanding Multi-Teacher On-Policy Distillation
Multi-teacher on-policy distillation aims to combine the strengths of RL-trained teachers in a single student, but how teacher signals affect parameter changes remains underexplored. Researchers studied Qwen3-1.7B with four domain...
Muon meets Tamed Langevin: Momentum Preconditioning beyond Convex and gradient-Lipschitz Potentials
The Muon optimiser has become a workhorse for large language model pretraining, delivering state-of-the-art efficiency gains over AdamW. Its defining trick is orthogonalising matrix-valued momentum, replacing every nonzero singula...