News
AI, cybersecurity, machine learning, scraping & programming news.
76 results on this page · clear filters
Twice Upon a Time: Complementary Representations for Time-Series Reasoning
The Problem With Single-View Time-Series Language Models Time Series Language Models (TSLMs) promise to bring the reasoning power of large language models to temporal data. They can answer questions, forecast future behavior, and...
Dog-Breed Text-to-image Flow Matching from Pretraining to Fine-Tuning on 4 Consumer GPUs
We generally perceive that training text-to-image diffusion models requires heavy compute: it is true if we aim at a comprehensive frontier model. This understanding prevents people from training their own models when getting star...
Two Clocks: Why Larger Rollout Batches Learn Slower but Fail on Schedule in Reinforcement Learning with Verifiable Rewards
Reinforcement learning with verifiable rewards RLVR relies on costly model-generated responses, motivating larger rollout batches and square-root learning-rate scaling. Reported to approximately preserve progress per sample with o...
AI Models Can Provably Hide Arbitrary Capabilities
Capability evaluations aim to surface dangerous model behaviors before deployment, but their reliability depends on the assumption that hidden capabilities can be elicited. Hickey and colleagues, together with Draguns and team, de...
Designing Protein Structures from Natural Language
A central challenge in de novo protein design is generating proteins with desired structural and functional properties. Existing design models typically require a dedicated input representation for each property, limiting the desi...
Prediction Is Not a Sufficient Memory State
A memory that reproduces every current prediction may still have forgotten how to learn from the next observation. We characterize this distinction for exact cumulative learning and attention. For smooth convex residual losses wit...
Inference-Time Steering Across Scaffolds and Epitopes for Sample-Efficient De Novo Nanobody Design
Generative molecular design typically relies on over-generation and post-hoc filtering. Inference-time steering methods like Feynman-Kac (FK) steering improve efficiency by biasing trajectories toward high-reward candidates, yet t...
Specialists Learn Faster: Knowledge Organization in Pre-training Shapes Knowledge Update Efficiency
Language models must continually update their knowledge to remain current. Most existing work focuses on making these post-training updates efficient, but this paper investigates a more foundational question: how the organization...
TabMF: Learning Dataset Representations with Tabular Foundation Models
Representations of supervised datasets serve as a foundation for higher-level machine-learning tasks such as dataset retrieval and distribution-shift monitoring. In practice, practitioners have needed reliable ways to characterize...
Spanning Diffusion and Flow-based Posterior Sampling via Exact Gaussian Conditioning
Flow-matching and diffusion models have become priors for linear inverse problems, yet most methods remain bespoke to a single class of trajectory prior. Plug-and-play alternatives exist but implicitly decorrelate the guided traje...