Machine learning news — deep learning, reinforcement learning, neural architecture search, diffusion models, and new ML frameworks and libraries.
A new arXiv paper (2609.36348v1) reports that adding cross-view class-token alignment to diffusion transformer training improves ImageNet linear-probing accuracy by 9.4% with the class token and 10.1% with mean-pooled pa…
A 35B-parameter model trained with a three-state autonomous search harness (Rubric, Answer, Verify) and a Seal Memory tool scored 72.83 on BrowseComp, outperforming comparable open-source systems, according to the arXiv …
A study posted to arXiv (2609.29769v2) found that Jev, a "decision model" that returns calibrated probabilities over permitted answers, can often substitute for three flash-tier LLM judges on nine panels from seven bench…
SemOPT, a semantic-guided framework for correcting LLM-based optimization models, achieves an average 7.6% accuracy improvement over the strongest baseline on complex datasets across seven optimization modeling benchmark…
Researchers proposed SCSP, a training-free framework that uses semantic compression prompts to select informative tokens for long-context embeddings instead of uniformly averaging all token representations, according to …
Encoder-based transformers DeBERTa, RoBERTa, and BART show no evidence of capturing the M-Heuristic pragmatic distinction between lexical causatives such as "Larry stopped the car" and periphrastic causatives such as "La…
E-MoE, a new method from researchers behind arXiv paper 2609.37533v1, builds the reverse process of masked diffusion models as a mixture of factorized distributions over a discrete shared latent set by the expert-routing…
A new arXiv paper (2609.37577v1) argues that the three standard proxies for evaluating pairwise LLM-as-a-judge reliability — position bias, transitivity, and pairwise agreement — are misleading because they are dominated…
A team of researchers posted arXiv paper 2609.36737v1 describing a differentiable, GPU-accelerated acoustic simulator that reconstructs vocal tract shape solely from speech, solving a notoriously non-convex inverse probl…
Researchers introduced RICE (Representations from In-Context Examples), a training-free method that extracts high-quality dense representations from decoder-only large language models by conditioning the model on a few i…
Researchers introduced Imagine3D-LLM, a multimodal large language model that decodes a small set of learnable summary tokens into a compact 3D Gaussian Splatting representation of a scene, supervised by a photometric rec…
Researchers introduced LIFT (Latent Information Feedback Transformer), a pretraining architecture and method that feeds deep-layer representations back to shallower layers by training models to predict both the next toke…
A parameter-matched study using a frozen HuBERT backbone found that a 64-dimensional prosody representation trained to predict log F0, voicing, Delta log F0, log energy, and spectral tilt produced no measurable increment…
A framework called IESR (Information Enhanced Structured Reasoning) achieved state-of-the-art results on the complex reasoning benchmark LogicCat with 24.28 EX and on the Archer dataset with 37.28 EX using only compact l…
A study of ten language models grounded in a maintained ontology corpus raised target-name recall from 0.265 unaided to about 0.92, but a verbatim copy baseline scored 0.964, leaving every model 0.022 to 0.067 below it, …
Researchers introduced RL-Focal, a two-stage reinforcement learning agent framework that routes and ensembles large language models, achieving an 8.48% performance improvement over the best individual LLM in a pool acros…
A recent electrical engineering graduate built an end-to-end Python pipeline that combines power system modeling, machine learning load forecasting, and battery dispatch optimization for renewable grid integration. The p…
Adversarial learning can serve as an effective post-training correction for pixel diffusion models, which generate RGB images directly without an autoencoder but systematically underrepresent fine-scale natural-image sta…
VideoLoop, a new method for long-form video understanding, counters "semantic thrashing" in multimodal agents by looping working memory instead of appending to it, according to the paper's authors. The approach targets t…
An AI system built by Markus Buehler's lab at MIT wrote its own atomistic simulation toolkit — a geometry generator, fracture solver, validation module, parameter scanner and three browser-based virtual labs — then ran h…