Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
Researchers compared six offline reinforcement-learning methods for distilling reasoning from large language models into smaller ones, finding that SFT, RFT, and RIFT produce nearly identical weight updates and accuracy,…
A new survey systematically reviews federated causal discovery and inference, organizing methods by design decisions, federation topology, and structural scope. The work formalizes the connection between causal discovery…
Researchers developed low-power analogue neural networks with trainable nonlinear connections, inspired by Kolmogorov-Arnold networks, achieving efficient continuous control tasks like robotic kinematics and photovoltaic…
Researchers introduced SurfBind, a surface-centric learning framework that directly models 3D molecular surfaces for accurate epitope prediction. SurfBind uses a Transformer-based architecture with patch-level surface mo…
Researchers introduced the degeneracy distillery, a method that automatically detects and resolves degenerate parameter combinations in physical models by estimating and flattening the Fisher information matrix. The appr…
Researchers introduced Sol Video Inference Engine, an agent-native full-stack acceleration framework for video diffusion models that achieves over 2x end-to-end speedup with near-lossless quality across models from 2B to…
Researchers introduced OmniPath, a multi-modal agentic framework that audits wheelchair accessibility by fusing OpenStreetMap data with aerial LiDAR to create high-fidelity 3D models. The system analyzes pedestrian surfa…
Researchers introduce ARIA, a framework that adaptively allocates training effort across regions of the conditioning space to improve distillation of conditional diffusion models. By focusing updates where teacher-studen…
Researchers introduced DriveStack-VLA, a framework that enhances Vision-Language-Action driving models with Bird-Eye-View representations and Render-Teacher Alignment to improve spatial intelligence. The model achieved s…
Researchers introduced Sesame, a diffusion-based molecular generation model that conditions on partial molecular structure and protein pockets via spatial density maps, enabling both de novo drug design and fragment-base…
Researchers introduced causal reinforcement learning (CRL), a framework unifying causal inference and reinforcement learning by modeling environments as structural causal models. CRL enables new learning paradigms includ…
Researchers introduced a multi-objective reinforcement learning framework for recommender systems that uses a Pareto-DQN agent with semantic embeddings to optimize engagement, diversity, and fairness as separate reward s…
Researchers formalized a new challenge called Member vs Generated Inference (MGI) to distinguish whether a sample is from a model's training set or generated by the model itself. They found existing methods fail and prop…
Researchers propose EMRFormer, a spiking neural network architecture that applies spike-driven transformers to automatic modulation recognition, achieving state-of-the-art accuracy while reducing theoretical energy consu…
Researchers introduced the apothem measure for computing robustness certifications in neural networks, achieving optimal certifications with linear oracle calls. They proved volume-optimal oracle-based algorithms are int…
A new study from arXiv shows that multilingual encoder initialization benefits streaming automatic speech recognition (ASR) only at low target-language data scales, with the advantage decaying as data increases. Across e…
Researchers propose NaviGen, a system that encodes user behavior history into executable instructions for personalized image and video generation, overcoming misalignment between AIGC pipelines and user intent. Using a d…
A new study on arXiv systematically examines the order of preprocessing techniques for sentiment analysis on Twitter datasets, finding that tokenisation is the most impactful technique while spelling correction is the le…
Researchers propose FlowR2A, a generative model that unifies scoring-based and anchor-based driving planning by learning reward-conditioned action distributions from dense trajectory-reward pairs. The method achieves sta…
Researchers propose Strategy-Guided Policy Optimization (SGPO), a method that replaces trajectory-level imitation with reusable strategy distillation to improve LLM reasoning. SGPO extracts structured strategies from str…