Machine Learning News

Researchers have developed a new emotion representation method called Dimensional Distribution Emotion State (DDES) to help museum curators predict the emotional responses artworks will evoke in visitors. The approach us…

Researchers at arXiv introduced PathoFM, an encoder-centric transformer for clinical time-series learning that uses three complementary pretraining objectives—Local Completion, Temporal Continuity, and Unsupervised In-Co…

Researchers have released RoMo, a large-scale dataset of in-the-wild human motions curated to overcome the limitations of existing small, high-fidelity motion capture and low-quality collections. The dataset employs a ta…

Researchers introduced Sentinel Challenge, a benchmark testing how decentralized embodied agents coordinate in city-scale outdoor environments by communicating in natural language to agree on safe meeting points while av…

Researchers have developed DuoGesture, a neuro-inspired dual-stream system that separately generates semantic and beat gestures for co-speech animation. The model uses a stochastic gate to coordinate when semantic gestur…

Researchers have identified a fundamental limitation in training LLM-based dialogue agents, showing that both static context reinforcement learning and prompt-based interactive RL suffer from context distribution shift t…

Researchers have developed InfoQuant, a training-free method that reshapes activation distributions in large language models to improve low-bit quantization efficiency. The approach, which uses Peak Suppression Orthogona…

Researchers developed HRVConformer, a deep learning architecture that classifies neonatal hypoxic-ischemic encephalopathy (HIE) by directly processing raw heart rate signals, achieving an AUC of 83.23% and accuracy of 74…

Large language models (LLMs) show reduced accuracy on math problems when simple details like names or numbers are changed, and a new study finds that using code execution methods does not improve this robustness. Researc…

MiniMax released the M2 series of Mixture-of-Experts language models, featuring 229.9 billion total parameters with only 9.8 billion activated per token, designed for agentic deployment. The models use agent-driven data …

Researchers introduced PolyFusionAgent, an interactive framework that combines a multimodal polymer foundation model with a literature-grounded design agent to predict polymer properties and generate novel polymer struct…

Researchers have developed Self-Verified Distillation, a method allowing large language models to improve themselves using only unlabeled prompts without external feedback. The approach, tested on Qwen3 models across mat…

Researchers at OpenPangu identified two failure modes in HiF8 W8A8 quantization-aware training for the OpenPangu-Embedded-1B model: amax saturation, which corrupts knowledge-sensitive representations through forward-pass…

Researchers have developed GAC, a noise-aware adaptive mixing controller for hybrid post-training that combines supervised fine-tuning and reinforcement learning. The method dynamically adjusts the mixing weight between …

Researchers introduced MM-CreativityBench, a new benchmark designed to test whether large multimodal models can solve open-ended, physically grounded problems by repurposing objects in non-obvious ways. The study found t…

Researchers have developed CARL (Contrastive Action-based Representations for Reusable Local Control), a new algorithm that exploits local dynamics regularity to learn reusable skills for hierarchical reinforcement learn…

Researchers introduced SPEAR (Sandboxed Prompt Engineer with Active Roll-back), a code-augmented agentic optimizer that autonomously rewrites prompts using a Python sandbox for structural error analysis, outperforming ex…

Researchers have developed RICE-PO, a policy optimization framework that converts retrieval interactions into localized learning signals for training reasoning-based retrieval agents. The framework addresses the credit-a…

Researchers have demonstrated that retrieval-augmented generation (RAG) can be understood as an in-context optimization process, where a single linear self-attention layer performs a gradient-descent step on a unified RA…

A new study reveals that large language models hallucinate on structured knowledge tasks due to systematic internal failures, not random errors. Researchers found that attention mechanisms disproportionately focus on sho…