Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
Researchers have developed Guidance Contrastive Policy Optimization (GCPO), a new algorithm that assigns per-token credit by contrasting model predictions under positive and negative prompts, addressing the limitation of…
Researchers have developed Aryabhata 2, a reasoning-focused language model for competitive STEM examinations, trained via reinforcement learning on PhysicsWallah's internal question banks. The model outperforms its base …
Researchers developed a target-informed self-supervised pretraining and model-ensemble strategy to improve cross-device generalization of ultrasound AI models without requiring new annotations. The method, tested on pedi…
Researchers have developed MechELK, a three-stage framework that uses mechanistic interpretability to extract hidden factual and reasoning knowledge from large language models. The framework, which combines sparse autoen…
Researchers have developed GeRaF, the first neural implicit learning method for reconstructing 3D geometry from radio frequency signals, enabling see-through-occlusion sensing without relying on RGB or LiDAR. The system …
Researchers have developed COLAGUARD, a new safety guardrail for large language models that transfers multi-step reasoning into a continuous latent space to reduce latency. In tests across ten moderation settings and eig…
Researchers have developed GenesisFunc, an automated pipeline that uses a multi-agent framework to generate high-quality, diverse training data for large language model function-calling. An 8B parameter model fine-tuned …
A new paired-minimum detectable effect (MDE) budget for 4-bit quantization benchmarks, derived from classical sample-size calculations, provides benchmark designers a one-line formula to pre-register reliability claims b…
Researchers have developed Orthogonal Concept Erasure (OCE), a new method for diffusion models that removes unwanted content while preserving overall image generation quality. The technique uses multiplicative parameter …
A team of researchers has developed a training-free multi-signal segmentation pipeline for the CVPR 2026 UG2+ Challenge's Dynamic Object Segmentation in Turbulence (DOST) track. The system combines RAFT motion estimation…
Researchers have developed a self-supervised deep learning framework that enhances Sentinel-1 Stripmap imagery by exploiting azimuth subaperture decomposition, generating paired training data without external sensors or …
Researchers have identified a critical underfitting problem in diffusion bridge models near the target endpoint, caused by a mismatch in noise levels between network input and regression target. The team proposes the Noi…
Researchers have developed a method to detect and track concepts within large language models (LLMs) by creating datasets that delineate specific ideas, training linear probes to identify those concepts across model laye…
Researchers found that LLM-generated reward functions for sparse reinforcement learning tasks fail in predictable ways, including reward flooding and API misunderstandings. A diagnostic-driven refinement method improved …
Researchers have developed TRACE, a trajectory-aware AI agent that uses large language model reasoning to optimize drug lead compounds by treating tool selection as a sequential decision-making process. The system outper…
Researchers at TradeArena found that large language model trading agents exhibit measurable pre-failure behavioral signatures, including planning embedding drift and effective-rank contraction, before financial drawdowns…
Researchers have developed SalsaAgent, a multimodal embodied language model that generates expressive, full-body salsa dance motions in response to a human leader and synchronized to music. The system extends a large lan…
Researchers have introduced Embodied3DBench, a benchmark designed to evaluate low-level spatial intelligence in Vision Language Models (VLMs) within embodied 3D environments. The benchmark includes over 21,000 question-a…
Researchers have developed GAP3D, a diffusion-based method that aligns vision-language model latents directly to patch-level image embeddings, enabling frozen generative models to use VLMs as prompt encoders without expe…
Researchers introduced TRACE, a training-free framework that stabilizes reconstruction trajectories in imaging inverse problems by coupling adjacent intermediate states. The method, which approximates proximal updates wi…