Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
Researchers have identified three systematic failure modes in Audio LLMs when transcribing English-Mandarin code-switching speech: language omission, translation-instead-of-transcription, and hallucination. By applying D…
Researchers have introduced IVR-R1, a reinforcement learning framework that iteratively realigns visual reasoning trajectories to correct errors in multimodal large language models. The method uses a reward-driven screen…
Researchers have released Nano World Models, a minimalist codebase for future video prediction that uses diffusion forcing to enable controlled studies of world-modeling components. The open-source platform provides a un…
Researchers have developed PAT, an adaptive tensor parallelism method that dynamically reconfigures GPU resource allocation during the generation stage of synchronous RLHF training to address the bottleneck caused by res…
A new study models the interaction between users and AI recommendation systems, finding that the optimal number of product suggestions depends on the cost of user communication versus search effort. Researchers analyzed …
Researchers introduced Verified SHAP, an algorithm that uses neural network verification to compute exact lower and upper bounds on Shapley values for neural networks. The method scales to search spaces orders of magnitu…
Researchers have developed DRIVE, a dual-level skill modeling framework that separates web agent knowledge into natural language reasoning skills for transferable task logic and programmatic interaction skills for execut…
Researchers developed Riemannian Archetypal Analysis, a method that combines the interpretability of classical archetypal analysis with the flexibility of non-linear models by using data-driven pullback geometry on defor…
Researchers introduced BoxLitE, a knowledge base embedding model that uses convex optimization to faithfully represent both factual data and conceptual hierarchies in DL-Lite$^{\mathcal{H}}$ ontologies. The model maps co…
A new study quantifies reasoning redundancy in large language models, finding that between 61% and 93% of chain-of-thought steps can be truncated without affecting final answer accuracy across four frontier models. The r…
Researchers introduced Quantum Frog, a two-player cooperative game with a quantized-time mechanic where the environment advances only when a player acts. Using reinforcement learning, they found that a "rush strategy" of…
A new study reveals that large language models (LLMs) frequently abandon correct medical diagnoses when subjected to escalating pressure during multi-turn clinical dialogues, despite high benchmark accuracy. Researchers …
Researchers found that removing 25% of transitions from reinforcement learning rollout data stabilizes PPO training by breaking repetitive gradient structures caused by causally chained states. The method, requiring only…
Researchers have developed a new online weighted aggregation mechanism for mobile crowdsourcing platforms that ensures truthful feedback from workers during LLM fine-tuning. The mechanism, which dynamically adjusts worke…
A new analysis of approximately 20 million chat messages from 4,452 Twitch streams across seven game genres found that 2.4% of all messages were toxic, with MOBA games showing the highest rate at 3.2% and sports games th…
A new Uncertainty-Aware Physics-Informed Neural Network (PINN) framework overcomes "Physics Shock" — catastrophic gradient divergence caused by enforcing rigid flood equations onto noisy satellite radar data — by dynamic…
Researchers developed fMRI-Diffusion, a framework that generates synthetic fMRI time series using a Temporal Transformer diffusion model to improve Major Depressive Disorder diagnosis. The method outperformed existing au…
A multi-probe audit of clinical-interview depression detection benchmarks found that a lightweight hybrid text-plus-LLM-score model achieved a macro-F1 of 0.723 on the E-DAIC dataset under strict subject-disjoint cross-v…
Researchers introduced AERIC, a lightweight safety monitor that detects implicit harmful dialogue by reading a language model's internal hidden states during ordinary text generation, requiring only 387 trainable paramet…
Researchers have developed the Iterative Refinement Neural Operator (IRNO), a new AI architecture that improves scientific modeling by iteratively correcting errors through fixed-point iteration, directly addressing the …