Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
Egyptian fractions, a method of expressing rational numbers as sums of distinct unit fractions, were used in Egypt as early as 4000 BC and remained the primary way to write non-integer numbers in Europe until the 18th ce…
Researchers introduced MR-DiffuSR, a 3D latent diffusion framework that uses high-resolution T1w structural priors to guide super-resolution of thick-slice FLAIR MRI scans, preventing anatomical hallucinations. The model…
Researchers introduced LDM-v0, a large decision model trained offline on trajectories from thousands of heterogeneous reinforcement learning environments, including robotics, autonomous driving, and video games. The sing…
Researchers propose Chorus II, a cross-request sparsity reuse framework for efficient image-to-video generation, achieving a 2.16× speedup by reusing sparse attention masks from similar historical requests. The method pr…
Researchers introduced the Swarm-Inspired Emergent Synchronizer (SIES), a graph-dynamical framework that learns local interaction rules for collective behaviors across graphs, dynamics, and tasks. SIES achieved synchroni…
Researchers developed a reinforcement learning-based method for digital twin-driven bearing health monitoring that adaptively aligns simulated and real vibration data, achieving 92.8% cross-equipment diagnostic accuracy …
Researchers introduced block-sparse featurizers (BSFs) to capture visual concept manifolds in neural network representations, showing that concepts are low-dimensional geometric structures rather than isolated directions…
A new survey from arXiv redefines continual learning for large language models as a closed-loop update-and-release problem within a versioned ecosystem, identifying three core challenges and five lifecycle design princip…
Researchers propose a novel neural network quantization method that learns quantization-aware linear paths in weight space to find low-loss subspaces, enabling direct quantization of the midpoint without performance degr…
Researchers introduced MJEPA, a joint-embedding predictive architecture for audio-visual learning that uses a single unified encoder and a single predictive objective. The model outperforms prior frozen baselines by over…
Researchers propose G-SPIN, a graph-based framework that corrects phonetic errors in ASR outputs by combining a graph neural network for candidate generation with a masked language model and LLM for contextual re-ranking…
Researchers present a low-resource machine translation system for the Tangkhul-English language pair, achieving a BLEU score of 39.97 using a ByT5-large model fine-tuned on 38,336 parallel sentences. The study highlights…
Researchers argue that neural network learning opacity stems from dynamical complexity, identifying sensitivity to weight initialization, feedback in gradient optimization, and sensitivity to training data as irreducible…
Researchers introduced Local Branch Routing (LBR), a token-level test-time scaling framework that expands a small local lookahead tree and uses a lightweight router to select the best branch, enabling efficient and train…
Researchers introduced the saturation index S(K) to determine when to stop collecting labeled examples in binary few-shot classification, proving it falls below a threshold when the covariance estimator is well-concentra…
Researchers propose SEMIR, a framework that replaces the pixel lattice with a parameterized graph minor to preserve thin-structure connectivity in segmentation tasks. The method achieves full-resolution inference without…
Researchers propose a hierarchical Bayesian framework for learning dynamical systems from multiple sparse datasets, modeling dataset-specific parameters as draws from a shared population distribution. The method embeds a…
Researchers released MacroLens, a multi-task benchmark for contextual financial reasoning under macroeconomic scenarios, covering 4,416 U.S. small- and micro-cap equities from 2021-2026. The benchmark integrates prices, …
A new study on holographic memory for zero-shot compositional reasoning in knowledge graphs found that while Holographic Reduced Representations (HRR) and Fourier HRR (FHRR) perform competitively on single-hop queries, t…
Researchers propose Dustin, a sparse verification framework for long-context speculative decoding in LLMs, achieving a 27.85x speedup in self-attention and 9.17x end-to-end decoding speedup at 32k sequence length with ne…