Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
Researchers propose ATOD, a hybrid online distillation algorithm that combines on-policy distillation and reinforcement learning to train small language-model agents for multi-turn tasks. ATOD uses an annealed schedule t…
Researchers at arXiv have discovered that activation patching, a key tool in mechanistic interpretability, contains hidden interaction effects (INT) that can distort causal attributions. These effects, which measure how …
A study evaluating boundary-condition fidelity for bottom-hole pressure and CO2 plume prediction in geological carbon storage found that conserving corner pore volume is critical for accurate truncated-domain simulations…
Researchers propose SD-GPS, a solver-driven framework for geometry problem solving that integrates autoformalization and theorem proposing. The framework uses a symbolic solver as an execution oracle to improve formaliza…
Researchers introduced SelectAnyTree, a promptable instance segmentation model for 3D forest LiDAR point clouds that delineates individual trees from a few clicks. The model achieves 78.2% Intersection over Union (IoU) f…
Researchers introduced QDiffusion-TS, the first quantum generative diffusion model for time series synthesis, validated on the IQM quantum processor. The model reduces trainable parameters by nearly three orders of magni…
Researchers introduced DMV-Bench, the first interactive benchmark for multimodal-agent visual memory, testing agents' ability to recall visual cues from product images in a simulated e-commerce environment. Their propose…
Researchers propose HIA-GAT, a heterogeneous graph attention network for frame-level traffic conflict risk prediction on freeways. The model outperforms baselines on NGSIM datasets, achieving AUC up to 0.867, and provide…
Researchers propose automation-in-design (AiD) using deep learning and generative AI to automate high-tech system design, demonstrated through e-drive and spatial dimensioning case studies. The framework aims to shift en…
Researchers introduced PEBS, a per-rater empirical-Bayes shrinkage estimator for calibrating reward models in RLHF, which reduces within-user held-out RMSE by 8.58% on PRISM and 9.66% on PluriHarms compared to the pooled…
Researchers introduced the Agent-Native Immune System (ANIS), a biologically inspired defense architecture embedded within autonomous agents' cognitive loops to counter runtime attacks like memory poisoning and tool-chai…
Researchers introduced P3Sim, a physical world modeling system that simulates future scene states from partial observations and incomplete 3D transformation signals. The system combines a learned world model, geometric c…
Researchers developed a distribution-based deep multiple instance learning method for tumor proportion scoring in non-small cell lung cancer, using only slide-level labels to predict zero-inflated beta parameters. The ap…
Researchers propose CoIn, a novel framework for 3D scene inpainting that bridges 2D inpainting models and Gaussian Splatting through a multi-stage consistency pipeline. The method handles both object removal and insertio…
Team HSA_CORAL submitted to the FinCausal 2026 shared task on extracting cause-effect relations from financial narratives via extractive question answering in English and Spanish. Their best system, GPT-4.1 Mini fine-tun…
Researchers used a developmental approach to study how neural language models learn statistical patterns, finding that Transformers first acquire abstract global statistics before local dependencies, with early over-gene…
Researchers at arXiv identified a memory-update gap in LLM agents, where accuracy drops from 92% to 77% when using bounded memory instead of full context, even with frontier models like gpt-5.4. The gap persists across m…
Researchers introduced the context-ready transformer, a recurrent neural network architecture that pre-contextualizes tokens before they enter a transformer block, achieving faster inference and competitive performance. …
Researchers propose a three-stage training paradigm to internalize future-aware planning in LLM agents, enabling them to simulate outcomes before acting. The approach, evaluated on search and math reasoning tasks, outper…
Researchers introduced LPES, a layer-specific positional embedding scaling method that mitigates the 'lost-in-the-middle' problem in LLMs by assigning distinct scaling factors to each layer, achieving up to 11.2% accurac…