All entries

arXiv:2609.26081v1 Announce Type: new Abstract: Fixed-budget robustness evaluation can select the wrong frozen vision encoder. An encoder that survives a shallow attack may lose most of that robustnes

arXiv:2609.25675v1 Announce Type: new Abstract: For a Dirichlet-smoothed transition model, the effect of adding one workflow trace to the training archive is an exact change in reference-weighted log

In light of recent events and media coverage, ai is in the spotlight and people are afraid. How I respond to those fears: If you are afraid of ai then you should also be afraid of all medical research

arXiv:2609.26092v1 Announce Type: new Abstract: One-to-one (O2O) matching enables Detection Transformers (DETRs) to perform end-to-end set prediction by assigning each object to a single positive quer

arXiv:2609.25688v1 Announce Type: new Abstract: Field robots operating across time of day and sensing modalities require accurate image correspondences within onboard time and resource budgets. Howeve

arXiv:2609.25860v1 Announce Type: cross Abstract: Sparse instance representations provide a compact interface for spatial LiDAR-camera and temporal past-current interaction in multimodal perception an

arXiv:2609.26520v1 Announce Type: new Abstract: Humanoid robots require diverse embodied experiences to acquire complex loco-manipulation and collaborative skills. However, existing humanoid data pipe

arXiv:2609.22724v1 Announce Type: cross Abstract: Mobile agents powered by foundation models now automate complex, multi-step workflows on real devices, but their trajectories can violate app-specific

arXiv:2609.26010v1 Announce Type: cross Abstract: Multi-agent reinforcement learning (MARL) commonly trains decentralized policies from scratch, requiring agents to acquire individual task competence

arXiv:2609.25518v1 Announce Type: new Abstract: Attributing language model outputs to their internal computations is an open problem in interpretability. Existing methods, which use causal interventio

arXiv:2609.26378v1 Announce Type: cross Abstract: Successful mobile manipulation requires coordinated base and arm motion while maintaining accurate spatial positioning. However, demonstration-trained

arXiv:2609.22599v1 Announce Type: new Abstract: Large language model (LLM) judges provide a flexible and scalable method for evaluating model and agent outputs, but their verdicts can be sensitive to

arXiv:2609.25500v1 Announce Type: new Abstract: Training data quantity and quality greatly affect object detection model performance, regardless of model architecture. When using object detection mode

arXiv:2609.23925v1 Announce Type: cross Abstract: We study whether LLMs can produce executable workflow artifacts that remain consistent across graph structure, tool implementation, schema bindings, a

arXiv:2609.25444v1 Announce Type: new Abstract: This work studies prediction parameterization for stochastic generative dynamics in diffusion models. Existing velocity-based generative models provide

arXiv:2609.26693v1 Announce Type: new Abstract: A coding agent must emit a valid tool call--a parseable invocation of a tool in the provided schema--before the harness can execute its chosen action. W

arXiv:2609.24706v1 Announce Type: cross Abstract: Autobiographical remembering supports identity, well-being, and social connection in later life, yet voice-based memory technologies largely rely on i

arXiv:2609.24061v1 Announce Type: cross Abstract: In this paper, we propose MECT, a speaker verification model that integrates the Mixture-of-Experts (MoE) mechanism into a CNN-Transformer backbone wi

arXiv:2609.24838v1 Announce Type: new Abstract: Medical agents increasingly combine general reasoning models with specialized clinical tools, yet their capabilities remain largely fixed by what clinic

arXiv:2609.25756v1 Announce Type: new Abstract: Precision medical robotics demands adaptive decision-making under strict safety, interpretability, and execution constraints. Although recent Vision-Lan

⚡ Meet Qwen-Audio-3.1! ASR, TTS & Realtime are fully upgraded, joined by two new models: TTS-Next for audio creation and ASR-Next for audio understanding. Five models, one complete audio stack: unders

arXiv:2510.21175v2 Announce Type: replace Abstract: Pre-trained vision-language models (VLMs), such as CLIP, have demonstrated remarkable zero-shot generalization, enabling deployment in a wide range

arXiv:2609.25853v1 Announce Type: new Abstract: Learned-memory methods store information in an explicit table and consume it through a separate reader, allowing addressing, storage, and reading to be

Meta is building a dedicated hardware device for its new Muse AI agent. The product, called Muse Charm, was briefly shown off by Meta CEO Mark Zuckerberg at the end of tonight's Meta Connect presentat

Meta is quickly iterating on its new Muse AI agent, announcing a bunch of updates today that make the bot more capable and able to chat with you in more ways. Muse agents are getting their own email a

Modern life comes with an unending, auto-populating to-do list. It never ceases to amaze me how I can be doing nothing at all, minding my own business, and suddenly something needs to be taken care of

arXiv:2609.25841v1 Announce Type: new Abstract: Metric reasoning is a critical and challenging task for Vision Language Models (VLMs), playing a pivotal role in embodied AI tasks such as robotic manip

arXiv:2609.26166v1 Announce Type: cross Abstract: Remote Sensing Change Captioning (RSCC), which aims to generate accurate and detailed linguistic descriptions of ground object variations from bi-temp

arXiv:2609.26103v1 Announce Type: new Abstract: Medical Image Super-Resolution (MISR) aims to enhance spatial resolution without requiring hardware modifications. Although deep learning has yielded pr

arXiv:2609.26025v1 Announce Type: cross Abstract: Human feedback can vary in cost and informativeness. Strong feedback can reveal severe errors but is costly, so cheaper quality ratings can help decid

arXiv:2602.23607v2 Announce Type: replace Abstract: Developing learning-based autonomy for microrobotic manipulation is difficult because physical trials are slow, variable, and poorly suited to large

Microsoft Corp. today unveiled Integrated Security Operations Center in Microsoft Defender as it rebuilds its security operations products around artificial intelligence agents. The service moves secu

MiMo-V2.6-Pro has an insanely high score of 46 on AA, putting it at the head of the opensource models available. It also costs pennies. Flash is not out on AA yet, but it costs less than half on datac

MiMo-V2.6-Pro is live on Wally. Day 1. @XiaomiMiMo's new open-weights flagship, top of the @ArtificialAnlys Intelligence Index for open-weight models. 320 tok/s, 2.4x the model maker's own API, in <24

arXiv:2609.25454v1 Announce Type: cross Abstract: Geographic measurements are often sparse, leaving large areas without labels for the quantities we want to map. Geographic implicit neural representat

arXiv:2609.25757v1 Announce Type: new Abstract: What is the least recurrent memory needed to reproduce a specified expert under partial observability? The instantaneous requirement is the conditional

Looking for the best way to restore/refine quality of an AI-generated 720p video to 2K I’m looking for advice on the best ComfyUI workflow for improving the quality of an AI-generated video. My workfl

arXiv:2609.25441v1 Announce Type: new Abstract: Legal argument mining supports passage classification, retrieval, and argument completion. This work introduces an expert-annotated dataset of 42 U.S. f

arXiv:2512.11472v3 Announce Type: replace-cross Abstract: Effective communication of robot touch intent is essential for safe and predictable physical human-robot interaction. While intent communicati

arXiv:2609.25331v1 Announce Type: new Abstract: Low-light image enhancement (LLIE) is an im- portant component of visual sensing systems operating under degraded illumination, including nighttime surv

arXiv:2609.25049v1 Announce Type: new Abstract: Large language models (LLMs) aligned for safety often suffer from over-refusal, incorrectly rejecting benign yet safety-related instructions. Prior stud

arXiv:2609.25166v1 Announce Type: new Abstract: Diffusion data-point unlearning is typically evaluated immediately after each deletion, even though subsequent requests may repeatedly update the same m

Standardizing independent evaluation, fairness, and interpretability for mechanism-informed generative AI in healthcare The post MLCommons Joins EU-Funded AIRIS Project to Build and Benchmark Next-Gen

arXiv:2609.26617v1 Announce Type: cross Abstract: Clinical decision making heavily relies on predicting the disease progression trajectory by seeking to understand patient's health status which is cha

arXiv:2609.26182v1 Announce Type: new Abstract: Multimodal embedding models are deployed at scale: retrieval indices, benchmark results, and behavioral audits all depend on the base model's exact outp

arXiv:2609.26272v1 Announce Type: new Abstract: Neural samplers are trained against an unnormalised target ildepi=e^{-E} with no samples from pi, which leaves the practitioner with no way to tell whet