All entries

arXiv:2609.31571v1 Announce Type: new Abstract: Many LLM training and inference methods, including RL and test-time scaling, depend on repeated sampling, but benefit only when the responses meaningful

arXiv:2609.30682v1 Announce Type: new Abstract: Self-supervised pre-training with Vision Transformers, including Masked Autoencoders (MAE), is difficult to apply to gigapixel scientific images. Random

arXiv:2509.25685v3 Announce Type: replace Abstract: We propose Structured-Diffuser, a diffusion planner that embeds task and motion structure directly into the noise model. Unlike standard diffusion-b

arXiv:2603.07096v2 Announce Type: replace Abstract: Robots that share space with people need human motion predictions with reliable uncertainty, not just accurate means. This paper presents a structur

arXiv:2609.31524v1 Announce Type: new Abstract: Surgical scene understanding is critical for computer-assisted intervention, yet laparoscopic cholecystectomy remains challenged by the complex anatomy

arXiv:2609.30832v1 Announce Type: cross Abstract: Perceived speech decoding based on non-invasive brain-computer interface (BCI) signals has been extensively studied in recent years. Research in this

arXiv:2609.30614v1 Announce Type: cross Abstract: Dataspace connectors decide whether a transfer may occur, not what the transferred value contains, tolerable for contracted applications, not for LLM

Hi everyone :) The amazing Swift finetunes of Qwen3.8 27B generate much fewer tokens at mostly similar benchmark performance to the original model, while repos like HyperQwen (formerly syv-ai/qwen38-2

arXiv:2609.30784v1 Announce Type: cross Abstract: This paper proposes an architecture for equipping large language models (LLMs) with audio-understanding capabilities without fine-tuning their weights

arXiv:2609.31024v1 Announce Type: cross Abstract: Sound matching can be formulated as optimizing synthesizer parameters against an audio-domain objective. However, objectives derived from generic audi

arXiv:2609.30576v1 Announce Type: new Abstract: Large-scale recommenders increasingly adopt the sequential generative recipe behind large language models, bringing the Transformer into recommendation

arXiv:2609.30969v1 Announce Type: new Abstract: Tactile information is essential for contact-rich manipulation tasks in robotics. Vision-based tactile sensors make it particularly easy to design end-t

arXiv:2609.30506v1 Announce Type: new Abstract: Humanoid hands require tactile feedback across the whole finger, not just the fingertip, to grasp and manipulate objects properly. Vision and propriocep

arXiv:2609.31170v1 Announce Type: new Abstract: Task-driven image restoration aims to improve both image quality and downstream task performance. However, existing methods predominantly focus on singl

arXiv:2609.31155v1 Announce Type: cross Abstract: Compressing a trained model yields a family of deployment candidates, and under domain shift the most compressed one need not be the one to deploy. We

arXiv:2609.31451v1 Announce Type: cross Abstract: The growing popularity of short videos has driven demand for one-click content creation. Visual templates turn uploaded images into personalized conte

arXiv:2609.31032v1 Announce Type: cross Abstract: Existing text-to-video (T2V) jailbreak methods mainly seek more effective or stealthier attack candidates. In guarded T2V systems, however, video gene

arXiv:2512.05836v2 Announce Type: replace Abstract: Recent advances in psychotherapy have focused on treatment personalization, such as by selecting treatment modules based on individual networks. How

arXiv:2609.30984v1 Announce Type: new Abstract: Text-to-speech needs written text in spoken form, and speech recognition output needs the reverse. For Khmer, neither direction has a maintained open-so

This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology. Who’s liable when AI agents go rogue? Over the past few months

arXiv:2609.30604v1 Announce Type: cross Abstract: Existing computer-use agent benchmarks do not fully evaluate agents acting as assistants. A useful assistant retrieves information across complex, mul

arXiv:2609.30854v1 Announce Type: cross Abstract: Autoregressive LLM inference at long context is bounded by memory bandwidth, not arithmetic throughput, and the binding resource shifts from model wei

arXiv:2609.30996v1 Announce Type: cross Abstract: The linear representation hypothesis (LRH) has become a standard lens for measuring and intervening on semantic information through the internal repre

The most important thing about Sonnet 5.5 is that it's now the model that powers the free tier on https://claude.ai - so all of this stuff can be done by free users ChatGPT's free tier is still GPT-5.

arXiv:2512.23619v3 Announce Type: replace Abstract: We investigate the topological structure of the optimal actuation landscape for fully-actuated N-rotor aerial vehicles. By formulating the design pr

The OpenAI-Hugging Face hack was enabled by weak sandboxing. It is great that Nvidia is releasing open source tools for sandboxing AI agents. OpenWorker, our open-source agent harness supporting cyber

arXiv:2509.26473v2 Announce Type: replace Abstract: Unified Multimodal Understanding and Generation Models (UMMs) increasingly combine visual understanding and image generation within a single interac

arXiv:2609.30705v1 Announce Type: new Abstract: While inference-time reasoning in large language models (LLMs) promises better decision making, its higher computational cost may not yield better econo

“The real story here isn't that AI escaped containment. It's that they built a container you could escape, shipped it into production training, and now they're surprised it escaped. If the room has a

arXiv:2609.31098v1 Announce Type: new Abstract: We introduce effective depth (Deff), a scalar diagnostic that treats the layer-wise residual stream of a transformer as a discrete-time process, measure

arXiv:2609.31341v1 Announce Type: new Abstract: Whether an information extraction pipeline should process page images or parsed text depends on the document, and the answer flips across the layout spe

We’ve updated Kitesurf, our Workers-based browser for AI agents, with WebMCP support, improved DOM performance, and terminal-based rendering. With over 730,000 Web Platform subtests passing, agents ca

arXiv:2609.30478v1 Announce Type: new Abstract: Convolutional neural networks trained on ImageNet are known to exhibit a strong preference for local high-frequency texture, an inductive bias that tran

arXiv:2604.07530v3 Announce Type: replace-cross Abstract: Scaling laws describe how language model capabilities grow with compute and data, but say nothing about how long a model matters once released

arXiv:2609.26174v2 Announce Type: replace-cross Abstract: We show that aligned vision-language models also condition refusal on a property of a request's form: whether an image is attached, holding ev

arXiv:2609.30563v1 Announce Type: new Abstract: Platform policies are increasingly tested on artificial users, making agent fidelity important. Yet convincing fake profiles could also manipulate perce

This is a big issue. At Anthropic, some philosophers worry that making AI safe for humans could be an injustice to the models themselves. For example, philosopher Harvey Lederman, now on Anthropic’s a

This user had Meta Muse order her medication at a lower price, organize the shipping, and manage the re-orders. (Have your agent look at Costplusdrugs!) https://x.com/SinaHartung/status/20995288671194

arXiv:2609.30690v1 Announce Type: cross Abstract: Ensuring operational safety in threat-prone environments remains a critical challenge for multi-UAV networks serving as aerial base stations. This pap

arXiv:2609.30877v1 Announce Type: cross Abstract: We study whether the linear condition-number dependence in the stochastic complexity of SAPD+ is necessary for nonconvex-strongly-concave minimax opti

arXiv:2609.30761v1 Announce Type: new Abstract: Most existing human motion generation (HMG) methods use cross-attention modules to inject text semantics, but ignore the importance of bidirectional mod

arXiv:2609.30358v1 Announce Type: new Abstract: Nanodrones require accurate, real-time state estimation under severe sensing and computational constraints. We present TinyCVIO, a visual-inertial odome

arXiv:2609.30878v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) provides dense teacher targets, but evaluates them only along student-sampled rollouts. When the privileged teacher f

arXiv:2609.30501v1 Announce Type: new Abstract: Although bilevel optimization (BLO) has emerged as a powerful framework for addressing many complex and nested machine learning problems in recent years

Today, with over 100 industry partners, we introduced the NVIDIA Open Agent Safety Platform, bringing together OpenShell and Sentry. Artificial intelligence is extraordinary technology that will advan

arXiv:2609.30906v1 Announce Type: new Abstract: Large language models (LLMs) excel at natural language processing but struggle to interact with external environments. Tool learning provides a promisin