Articles & Guides

A new arXiv paper argues that one-shot benchmark gains are not enough to judge agent optimizers. In a two-phase continual-learning setup, methods diverged sharply once new tasks were introduced.

A new arXiv paper proposes using the Lyapunov characteristic exponent as a physics-informed dense reward for stabilizing an inverted pendulum with vertical motion. The reported agent not only rediscovered Kapitza-like oscillatory stabilization but also damped the pivot motion into a strictly upright state.

A new arXiv paper proposes the DVM-HALL framework and the Net Human-Agent Score to rethink loyalty in autonomous commerce. The model treats trust, delegation, machine experience, and verifiable execution risk as core parts of brand choice.

Microsoft’s latest Patch Tuesday addressed a record 570 security vulnerabilities across Windows, Office and other products. The company says AI-assisted discovery contributed to the unusually large update.

A new arXiv paper introduces TRACE, a dense credit-assignment method for agentic reinforcement learning. It uses a frozen reference model to estimate state values and turn final-answer supervision into per-tool-call rewards.

A new arXiv paper on the ABAW11 challenge argues that valence-arousal estimation, expression recognition, and action unit detection should not necessarily share the same fusion strategy.

A new arXiv paper extends empirical Bayes variational autoencoders to jointly model tumor growth, time to dropout, and genomic covariates. The work combines neural dynamics with semi-mechanistic pharmacometric structure.

A new arXiv paper proposes VisionScreen, a vision model that extends the Screening mechanism from language modeling to image recognition. Instead of assigning relative softmax weights to all patches, it aims to explicitly exclude low-relevance visual tokens.

A new arXiv paper proposes modeling choreography as a sequence of interpretable atomic movements rather than only as continuous motion. The approach separates dance planning from motion completion to improve structure, rhythm alignment, and controllability.

A new arXiv paper introduces CAVE-ABSA, a constraint-aware framework for generating and validating counterfactual examples in aspect-based sentiment analysis. Instead of flipping a whole sentence’s polarity, it aims to change only the sentiment tied to a target aspect.

A new arXiv paper introduces CF-Net, a multimodal model for recognizing ambivalence and hesitancy in unconstrained video. Instead of looking for prototypical emotion cues, it focuses on subtle inconsistencies across vision, audio, and text.

DeltaMerge-LowRes explores whether low-resource NLP adaptation can avoid costly joint language-task fine-tuning. It trains a language delta and a task delta separately, then studies how different merge rules change model behavior.

A new arXiv paper introduces PlumeQuant, a diagnostic framework for checking whether methane plume masks, IME, plume length, emission rates and uncertainty estimates are internally consistent. The study shows that published scalar quantities often do not uniquely determine the plume boundary.

A new arXiv paper improves the theoretical mixing bound for Dikin walks on polytopes. Using a scaled Lee–Sidford metric, the author proves a d^2.25 warm-start mixing bound for exponential sampling.

A new arXiv paper introduces Peak-End-Net, a lightweight framework for video aesthetic assessment inspired by the psychological peak-end rule. Instead of treating all frames equally, it emphasizes salient moments and the ending of a video.

A new arXiv paper introduces HealthClaw, an open-source agent architecture designed for ongoing personal health support. Instead of treating each query in isolation, it updates private memory as routines, preferences, measurements, and risks change.

A new arXiv study proposes a two-step unsupervised clustering strategy for multimodal cardiac PET/MRI data. The method generates automated text and bullseye reports that align reasonably well with cardiac imaging specialists’ observations.

A new arXiv paper introduces SIVA-RL, a framework that assigns visual-alignment supervision based on the observed effect of image interventions. The goal is to make vision-language models rely more reliably on visual evidence during reinforcement learning.

A new arXiv paper introduces VAIOM, a decoder-only Transformer designed for probabilistic next-return modeling on one-hour foreign-exchange bars. The model keeps financial observations continuous at the input while using discrete return buckets for training and evaluation.

A new arXiv paper formalizes how audit-selection histories can expose whistleblowers and proposes a private auditing framework based on continual counting. The work argues that simple randomized response is fundamentally limited in this setting.

PyTorch-Triton 3.7 introduces Triton Plugin Extensions, a runtime mechanism for loading compiler passes, MLIR dialects, and DSL extensions without forking Triton. Meta’s TLX is the first major beneficiary, enabling lower-level GPU kernel control in stock Triton.