Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
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 …
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 at Qwen2.5-3B-Instruct found that supervised fine-tuning (SFT) causes greater disruption to internal computational circuits and more catastrophic forgetting than reinforcement learning (RL) when adapting larg…
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 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 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 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 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…
A new 306M-parameter language model architecture, the Cognitive Categorical Transformer (CCT), achieved 21.27 validation perplexity on WikiText-103, a 12% relative improvement over a fine-tuned GPT-2 Small baseline. The …
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 introduced Thoughts-as-Planning, a framework that formalizes reasoning chain optimization in large language models as a sequential decision-making process over a latent semantic space. The method models …
A new study analyzing 17 language models from 410 million to over 100 billion parameters found that instruction-tuned systems systematically collapse linguistic entropy along discourse and structural dimensions, with mea…
Researchers have developed a lightweight multimodal large language model framework for defect grading of power transmission equipment, achieving state-of-the-art performance while reducing manual annotation costs. The ap…
RightNowAI released RightNow-Arabic-0.5B-Turbo, a 518M-parameter Arabic-specialized language model that outperforms all existing sub-1B open models on Arabic benchmarks while running on edge devices. The model, built by …
A study of ClinicalTrials.gov records found a marked increase in AI-related clinical trials over time, with recent growth in references to machine learning, deep learning, chatbots, GPTs, and large language models. China…
Researchers have demonstrated a blind False Data Injection Attack (FDIA) using an Autoencoder that learns the measurement manifold and generates perturbations aligned with the Jacobian null space, evading both residual-b…
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 introduced COM, a strategy that enforces geometric constraints on time series token embeddings to preserve their inherent continuity and ordinality in large language models. The approach, detailed in a n…
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 …
Tensors enable hardware acceleration by leveraging GPUs and TPUs to perform parallel mathematical operations efficiently, making them essential for training neural networks. They also support automatic differentiation, w…