Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
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 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 UniMVU, a unified multimodal video understanding framework that uses instruction-aware gating to dynamically balance the importance of different input modalities like video, audio, and depth ma…
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…
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…
Researchers have developed PaGeR, a framework that adapts existing 3D foundation models designed for perspective images to reconstruct full 360-degree scenes from single panoramic images. The model predicts scale-invaria…
Researchers have developed Lie group embedded dynamical neural networks (LieEDNN) that enable stable, learnable dynamics on smooth manifolds by treating Lie groups as intrinsic representations of continuous symmetry. The…
A new study finds that vector representations exported from large language model summarization systems can leak sensitive information, even when source documents remain access-restricted. Researchers auditing clinical di…
Researchers have developed Conv-to-Bench, a framework that automatically converts real-world user-assistant dialogues into structured evaluation benchmarks for large language models. In programming tasks, the system achi…
Researchers have introduced FEPoID, a training-free method for automatically selecting intermediate layers in large language models to improve hallucination detection. The approach outperforms existing criteria and detec…
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 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 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 have developed VesselSim, a two-stage framework for 3D blood vessel segmentation that eliminates the need for expert annotations during training by generating 16,500 synthetic angiographic volumes. The system…
Researchers have developed RadarSim, a unified differentiable renderer that uses multimodal neural fields to generate high-resolution Doppler radar range images by leveraging camera data. The system addresses the low spa…
Researchers have introduced GEM (Geometric Entropy Mixing), a framework that reformulates LLM data curation as a variational problem on a hypersphere to overcome flaws in human taxonomies and Euclidean clustering. By dec…
A new study from researchers measuring validity-correctness tradeoffs in structured outputs for small language models found that hard schema constraints significantly degrade answer accuracy despite perfect schema compli…
Researchers have introduced Neural Bayesian Sequential Routing (NBSR), a framework that models neural inference as active evidence accumulation over a hierarchical Directed Acyclic Graph using a Dirichlet-Categorical con…
A new study reveals that language model reasoning trajectories during test-time sampling cluster into "reasoning basins," causing majority votes to favor stable but potentially incorrect answers. The researchers introduc…