Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
Researchers at the University of Oxford found that observable patterns in latent reasoning models, such as BFS-like frontiers and decodable arithmetic, also appear in control models lacking the proposed recurrence or cur…
Researchers introduced SciAgentArena, a benchmark of approximately 200 tasks with stepwise verification to evaluate AI agents in real-world scientific research scenarios. Testing revealed that current agents perform well…
Researchers introduced AfriSUD, the first large-scale collection of syntactically annotated treebanks for nine African languages, using the Surface-Syntactic Universal Dependencies framework to capture typological featur…
Researchers at an undisclosed institution reverse-engineered Apple's Metal 4.1 tensor compute path on the M4 Max GPU, revealing that the fp8 matmul2d operation is emulated rather than hardware-accelerated. The study, pub…
Researchers from a study on arXiv introduce HieraRAG, a hierarchical framework for determining optimal granularity in RAG benchmark construction, using 5,872 synthetic QA pairs from FineWeb-10BT across three dimensions. …
A new study from researchers testing adapter composition in large language models found that geometry-aware merging strategies, which enforce orthogonality or directional independence in parameter updates, provide no con…
A new study quantifies the rate at which undesirable behaviors transfer from teacher to student language models during distillation, a phenomenon known as subliminal learning. Researchers steered Llama-2-7B-Chat and Qwen…
Researchers have introduced Rotary Value Embeddings (RoVE), a parameter-free modification to Rotary Position Embeddings (RoPE) that makes value pathways position-sensitive by rotating values simultaneously with keys. Thi…
Researchers have identified specific neural pathways in large language models that carry anchoring bias signals, where irrelevant numbers in prompts skew numerical reasoning. Using attribution-based circuit localization …
Researchers have developed a least-action-guided diffusion (LAPG) framework that enforces physical consistency in generative models during inference, addressing the challenge of reliable extrapolation beyond training dat…
Researchers fine-tuned three small language models—Phi-3-mini, Qwen2.5-3B, and Mistral-7B—using QLoRA on biomedical claim verification datasets, finding that Mistral-7B outperformed GPT-4o and GPT-5 by up to 12% F1 at a …
Researchers introduced FreeBridge, a variational Schrödinger Bridge model that infers continuous cellular transition dynamics from high-content imaging assays where only endpoint populations are observable. By constraini…
Researchers have developed FlowBank, a three-stage framework that optimizes LLM-based multi-agent systems by precomputing a compact bank of reusable workflows and adaptively selecting among them per query. The approach a…
Researchers have demonstrated that Direct Preference Optimization (DPO) simplifies the fine-tuning pipeline for large language models while improving computational efficiency and achieving competitive performance. The em…
Researchers have developed LakeFM, a foundation model for aquatic ecosystems trained on large-scale simulated and observed lake data. The model learns representations of lake-level characteristics and achieves superior f…
Researchers at an academic medical center developed a pre-response classifier that predicts the risk of a user rejecting an LLM-generated clinical response, achieving an AUROC of 0.719 over 4.5 months of user feedback. T…
Researchers have developed a framework for strategic decision support in AI agent systems, where agents act on behalf of users and require human or tool assistance to prevent consequential errors. The framework minimizes…
Arbor, a multi-agent framework developed by researchers, introduces structured tree search as a cognition layer for autonomous agents operating in large, stateful action spaces. The system maintains an explicit search tr…
Researchers have developed Context-Centric Feature Fusion (CCFF), a framework that uses two attention-based modules to improve detection of co-occurring objects in autonomous driving. The system achieved a Category-level…
Researchers have developed YOLO-AMC, an improved YOLO architecture integrating attention mechanisms for building crack detection, achieving mAP@0.5 of 0.9917 on test datasets. The model outperforms baseline YOLOv11n and …