All entries

arXiv:2609.37535v1 Announce Type: new Abstract: In the softmax output layer, a rare token receives a small positive logit gradient on most steps and a much larger negative gradient on the few steps wh

arXiv:2609.36117v1 Announce Type: new Abstract: Securing modern AI systems against backdoor attacks remains an open challenge and requires fundamentally principled estimates of the adversary's budget

arXiv:2609.37297v1 Announce Type: new Abstract: Cross-skeleton motion generation trains generative models to carry action structure and motion intention from one body to another. Yet a target motion t

arXiv:2609.37096v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) consistently struggle with fine-grained visual counting, yet the underlying causes remain poorly understood. In

arXiv:2609.37702v1 Announce Type: cross Abstract: Class Incremental Learning (Class-IL) requires models to learn new classes over time while preserving previously acquired knowledge without access to

arXiv:2609.37816v1 Announce Type: new Abstract: Inpainting 3D Gaussian Splatting scenes, a key challenge in 3D editing, requires generating plausible content within a masked region of 3D space. Prior

arXiv:2609.37687v1 Announce Type: new Abstract: Active test-time adaptation (ATTA) improves robustness under distribution shift by updating a deployed model during inference while selectively querying

arXiv:2609.36635v1 Announce Type: cross Abstract: Bug validation asks a coding agent to produce an executable witness for a reported bug. The witness combines a concrete input with a testing harness a

arXiv:2609.37004v1 Announce Type: new Abstract: We present World2Motion, a framework that generates scene-aware 3D human motion and corresponding video from a single image and a text prompt. While exi

arXiv:2609.36438v1 Announce Type: new Abstract: Autonomous driving requires choosing a safe and efficient plan as surrounding traffic evolves. Generate-and-select planners propose multiple trajectorie

arXiv:2609.38059v1 Announce Type: cross Abstract: Real-world robot learning is constrained by the cost of collecting experience and evaluating candidate behaviors. Video generation models offer a scal

arXiv:2609.37552v1 Announce Type: new Abstract: While contact-rich manipulation requires deliberate regulation of interaction forces, recent approaches to robot manipulation learning predominantly rep

arXiv:2609.38121v1 Announce Type: new Abstract: KV cache memory and bandwidth costs grow with context length and batch size, which limits efficient long-context inference. To address this bottleneck,

arXiv:2609.36136v1 Announce Type: new Abstract: Compact OCR-specific vision-language models achieve strong document parsing performance, but often rely on costly supervision and focus primarily on vis

arXiv:2609.37594v1 Announce Type: new Abstract: Uncertainty estimates tell us how unsure a model is, but not why. Without knowing which parts of an input influences a model's uncertainty, we cannot te

🚨 Yesterday, the 'White House Accord on Super Intelligence' was signed. What was supposed to be about AI safety and accountability was instead a PROBLEMATIC endorsement of self-regulation. My comments

arXiv:2609.37902v1 Announce Type: new Abstract: Existing LLM routers choose among models using static per-model costs. We show that open-weight inference markets introduce a second, largely ignored de

arXiv:2609.36837v1 Announce Type: new Abstract: Generative super-resolution models can turn portable 64 mT MRI into images that look like 3T scans, and the field evaluates them with PSNR, SSIM, and pi

arXiv:2609.36661v1 Announce Type: new Abstract: Visual reprogramming is a parameter-efficient method for adapting pretrained models, yet its training can remain computationally expensive: even with a

Your agent got the right answer. How much work did it take to get there? We worked with @NousResearch/@Teknium on a hands-on walkthrough of NVIDIA NeMo Relay to collect traces for Hermes Agent. Run tw

arXiv:2609.37494v1 Announce Type: new Abstract: Multiple-choice benchmarks are cheap to grade and are running out of room, and the standard remedy, writing harder items, is slow and repeated for every

arXiv:2609.37883v1 Announce Type: new Abstract: Pre-trained language models (PLMs) with encoder-based architectures have shown impressive capabilities in zero-shot cross-lingual transfer for various l

arXiv:2602.02848v2 Announce Type: replace Abstract: Advances in large language models have driven strong performance across many tasks, but their memory and compute costs still hinder deployment. SVD-

arXiv:2609.37078v1 Announce Type: new Abstract: Time series modeling increasingly demands high-quality supervision, yet target observations remain scarce - exogenous inputs are broadly available, but

1501: Pope Alexander VI criticizes Gutenberg’s printing press safety “The art of printing can be of great service in so far as it furthers the circulation of useful & tested books; but it can bring ab

arXiv:2609.31686v1 Announce Type: new Abstract: Existing aviation emissions inventories lack accurate trajectory data for high-resolution social cost and health impact assessment. This paper develops

arXiv:2609.34035v1 Announce Type: new Abstract: Tracking any point of a dynamic scene in metric 3D - in absolute meters, not up to an unknown scale - underpins 3D and 4D reconstruction, robot navigati

arXiv:2609.31756v1 Announce Type: new Abstract: Does high image fidelity imply readable screen content in 3D Gaussian Splatting (3DGS)? We introduce 3DGS-SC, a controlled static screen-content dataset

Getting artificial intelligence into production has become the real test for enterprises. As the proof-of-concept phase ends, harder questions about cost, data and control are taking its place. That s

I wanted a fun way to visualize and stress-test a multi-agent ecosystem, so I pointed it at my favorite MMO (a vanilla-era private server emulator). Live view: https://design.kristiantalley.com/projec

I’m building a Polish General purpose legal Model that drafts documents, answers questions using legal sources, and has enough coding ability to handle some automation. The workflow is very tool-heavy

arXiv:2609.33467v1 Announce Type: new Abstract: When post-training large language models on tasks with semi-verifiable rewards, there are many factors (training steps, base model size, training order,

arXiv:2609.32341v1 Announce Type: new Abstract: Transformers and state-space models (SSMs) are two prominent sequential learning architectures, yet their comparison remains largely empirical and exist

arXiv:2609.31677v1 Announce Type: new Abstract: Face recognition is widely deployed in surveillance, access control, and forensic workflows, yet accuracy degrades sharply once the face is occluded by

arXiv:2609.34015v1 Announce Type: cross Abstract: Phishing remains one of the most common vectors for financial and identity fraud, and most detection systems still rely on inspecting a page's URL, HT

arXiv:2607.14522v2 Announce Type: replace Abstract: We formulate reinforcement learning (RL) in continuous time with discrete state spaces and possibly arbitrary action spaces via a stochastic control

arXiv:2609.33542v1 Announce Type: new Abstract: Direct torque sensing is a growing need in the robotics community to enable precise control and interactions where torque estimation from motor current

arXiv:2506.17316v2 Announce Type: replace-cross Abstract: This paper proposes a family of graph metrics for measuring distances between graphs of different sizes. The proposed metric family defines a

arXiv:2609.33457v1 Announce Type: new Abstract: Many dense-prediction benchmarks evaluate rare events by pooling prediction and target over spatial blocks, thresholding each, and scoring the contingen

arXiv:2609.32890v1 Announce Type: new Abstract: Language models are increasingly evaluated as vulnerability detectors, and scores reported for similar models differ widely between papers. We measured

arXiv:2510.26184v2 Announce Type: replace Abstract: Public resource allocation involves distributing resources, including urban infrastructure, energy, and transportation, which are typically limited

arXiv:2609.35217v1 Announce Type: cross Abstract: Modern probabilistic machine learning models increasingly produce multivariate outputs with complex dependence structure, from multi-step time-series

arXiv:2609.32290v1 Announce Type: new Abstract: It has recently been found that deep learning often occurs at the 'edge of stability (EoS),' where the maximum Hessian eigenvalue of the model is stabil

arXiv:2509.11070v4 Announce Type: replace-cross Abstract: We develop a stochastic approximation framework for learning nonlinear operators between infinite-dimensional spaces utilizing general Mercer

arXiv:2609.31877v1 Announce Type: cross Abstract: Cloud-based Large language model (LLM) services create a network-level traffic side channel that can expose model, prompt, and task behavior despite e

arXiv:2609.33424v1 Announce Type: cross Abstract: Self-supervised pretraining learns representations that are broadly transferable across downstream tasks, yet direct fine-tuning can be suboptimal due