Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
A developer built a Pluribus-style poker AI from scratch, implementing Counterfactual Regret Minimization (CFR) and its variants to solve imperfect-information games. The project achieved Nash equilibrium convergence in …
A toy transformer retains provably predictively defunct belief state data in its residual stream, shedding it only under sufficient capacity pressure. Experiments extending Shai et al. 2024 show that information about a …
A developer built Signal-OSS, a GitHub Action that scores new issues from 0 to 10 using heuristics and an optional LLM tiebreaker, automatically posting tailored checklists to help contributors improve low-quality report…
Deltatensors, a new open-source tool, compresses fine-tuned neural network model deltas into small .wdelta files, achieving near-lossless compression with sub-1% perplexity difference. Tested on Qwen2.5-0.5B fine-tuned o…
An ML engineer built a system that automatically rolls back machine learning models before they harm production data by routing a small percentage of live traffic to a canary model, continuously measuring its error rate …
Agencies including WPP, Dentsu, and Butler/Till are racing to develop AI agents for media buying and planning, aiming to gain a competitive edge. However, brands like Hyundai are using the same technology to bring market…
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 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 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 paper reveals that diffusion models and flow matching models are unified under the geometry of Wasserstein space, where diffusion follows a gradient flow of free energy and flow matching follows a geodesic, explain…
Researchers reconstructed GRACE-like terrestrial water storage anomalies back to 1940 using a spatio-temporal graph neural network (MTGNN) applied to South America. The model achieved high correlations and low bias, outp…
Researchers developed an automated pipeline to explore heterogeneous 4-expert mixture-of-experts architectures, generating 4,463 candidate models over 28 days. The search was biased toward the AirNet family due to an enu…
Researchers propose ModTGCN, a modularity-aware graph neural network for text classification that jointly optimizes cross-entropy and a modularity-based auxiliary objective to promote class-coherent document communities.…
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 developed a hybrid machine learning approach combining EfficientNetB0 feature extraction with Random Forest classification to achieve 94.58% accuracy and sub-millisecond inference for real-time melt pool moni…
Researchers introduced the MELD dataset to evaluate whether embedding models capture mathematical equivalence, finding that current models group statements by terminology rather than underlying math. They proposed a cont…
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 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…
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 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…