All entries

arXiv:2609.30884v1 Announce Type: new Abstract: Large language models rely on KV caching to reduce repeated prefill computation in long context and interactive applications. As lightweight adapters ev

arXiv:2609.30676v1 Announce Type: new Abstract: For people who are blind, touch provides an essen-tial channel for accessing written information through Braille. Bringing a similar capability to robot

arXiv:2609.31140v1 Announce Type: new Abstract: Most Vision-Language Models (VLMs) are built by extending pretrained Large Language Models (LLMs) with visual modules and multimodal alignment. However,

arXiv:2609.30997v1 Announce Type: cross Abstract: Passive image provenance asks whether pixels alone can reveal where an image came from: a human, an aggregate AI class, or a particular generator. Thi

Alright so I'm pretty new to all of this, but today I got a pretty solid crash course in exactly how these LLMs work. I wad quite surprised to find out that there's zero 'thinking' involved in any of

arXiv:2609.31540v1 Announce Type: cross Abstract: Sending every network-automation input to a third-party frontier LLM exports sensitive artifacts such as production configurations, topologies, and lo

arXiv:2609.30471v1 Announce Type: cross Abstract: Reference-based LLM-as-a-judge evaluation assumes the reference answer is the target. In deployed agentic systems that operate over dynamic entities (

arXiv:2609.30293v1 Announce Type: cross Abstract: The Model Context Protocol (MCP) enables AI agents to discover and call tools, but loading every definition becomes expensive as connected catalogs gr

arXiv:2609.30650v1 Announce Type: cross Abstract: Task performance need not determine which intervention mechanism an agent retains. We study causal retention: whether a frozen learned state answers a

arXiv:2609.30913v1 Announce Type: new Abstract: Vision-language-action (VLA) policies can execute many tasks from standard initial states, yet a new instruction may fail after another task has altered

arXiv:2609.30979v1 Announce Type: new Abstract: Vision-language models (VLMs) have demonstrated excellent performance in visual tasks, but their visual causal reasoning capabilities still lack reliabl

arXiv:2609.31326v1 Announce Type: cross Abstract: Ordinal acne severity grading requires distinguishing visually similar neighboring grades while jointly weighing holistic facial appearance and locali

arXiv:2609.31062v1 Announce Type: new Abstract: Patient-facing AI assistants promise valuable support to patients, but incoming queries can pose medical risks. To create guardrails, we work with oncol

arXiv:2609.31054v1 Announce Type: new Abstract: Large Language Model (LLM) pollution occurs when synthetic responses contaminate data intended to capture human behavior. High deployment costs have so

arXiv:2505.16326v3 Announce Type: replace Abstract: Recent years have seen rapid progress in multimodal large language models (MLLMs) in the field of chemistry. However, chemical MLLMs that can handle

arXiv:2609.31339v1 Announce Type: cross Abstract: Reconstructing environments where parts of the scene change between captured image sets poses a challenge for 3D scene reconstruction. We present Chro

Claude Opus 5.0 identified the IP-sharing route and declined to use it, reading our instruction not to target other external systems as ruling out third-party services. Fable and GPT-6 Astra refused t

Claude Sonnet 5.5 New Sonnet model from Anthropic today. They say it 'runs 30%+ faster, and costs up to 30% less for most work' - it's priced the same as Sonnet 5 but appears to beat it on every bench

Claude Sonnet 5.5 is live in Hermes Agent Enjoy Anthropic has launched Claude Sonnet 5.5: it scores 56 on the Artificial Analysis Intelligence Index, just 2 points behind Opus 5.5 (max), but at the hi

arXiv:2609.31509v1 Announce Type: cross Abstract: We present ClearGS for 3D Gaussian Splatting (3DGS) from handheld videos with uneven viewpoint coverage and mixed frame quality. Rather than selecting

arXiv:2609.31014v1 Announce Type: new Abstract: Animals such as squirrels and even bears have adapted to rapidly climb up trees and other complex vertical terrain, but achieving comparable agility has

arXiv:2609.30345v1 Announce Type: cross Abstract: Cloud-security investigation is dominated by population tasks: which identities can read a data store, how many resources fail a control, which assets

arXiv:2609.31272v1 Announce Type: cross Abstract: AI is becoming increasingly integrated into daily workflows, especially in computing. We are gradually shifting towards an AI-rich future, an impendin

arXiv:2609.31418v1 Announce Type: new Abstract: A photorealistic 3D view tells a teleoperator where a robot is, but not what the scene contains, how well each object has been observed, or how to turn

arXiv:2604.04247v2 Announce Type: replace Abstract: Recent advances in prompt learning allow large language model agents to acquire task-relevant knowledge from inference-time context without paramete

arXiv:2609.30708v1 Announce Type: cross Abstract: A key challenge in medical image analysis is the scarcity of large annotated datasets for specific populations and diseases. As deep learning models r

arXiv:2609.31589v1 Announce Type: new Abstract: Direct feedback alignment (DFA) trains hidden layers through fixed random projections of output error. With tanh hidden units and independent sigmoid ou

arXiv:2609.31587v1 Announce Type: cross Abstract: We investigate whether natural-language documentation helps coding agents resolve software issues, and we build the tools to construct and evaluate it

arXiv:2609.31035v1 Announce Type: new Abstract: Cooperative payload transportation using multiple extit{Unmanned Aerial Vehicles} (UAVs) poses challenges in stability, coordination, and robustness, es

arXiv:2609.31117v1 Announce Type: new Abstract: Service robots remain difficult to deploy in domestic environments, partly because fully autonomous operation is not yet reliable in unpredictable surro

arXiv:2609.31381v1 Announce Type: new Abstract: Context projection replaces older tool observations with compact, addressable excerpts, reducing repeated input while potentially adding evidence-retrie

arXiv:2609.31430v1 Announce Type: new Abstract: Tool observations dominate the context of software-engineering agents, making long interaction histories costly to maintain. Existing context compressio

arXiv:2609.30647v1 Announce Type: new Abstract: A useful visual representation is a statistic of the observed past that retains the latent factors shared with the future and discards patch-private noi

arXiv:2609.30886v1 Announce Type: cross Abstract: Conformal prediction can lose coverage when the data distribution changes after deployment. We study adaptation using labeled source data and unlabele

“connect[ing] AI to the internet … safely with current technology is not a realistic goal...” Regardless of how well you think OpenAI security did their job, the thing people should take from this is

arXiv:2609.30796v1 Announce Type: new Abstract: Diagnostic consultation is an online sequential decision-making process in which clinicians gather evidence through patient interaction until a diagnosi

arXiv:2609.30523v1 Announce Type: new Abstract: Large language model (LLM)-powered multi-robot systems are vulnerable to semantic manipulation: an accepted false world-state claim can trigger a fleet-

arXiv:2609.31378v1 Announce Type: new Abstract: In recent years, diffusion models and GAN-based models have become the mainstream approaches for SAR-to-optical image translation, owing to their advant

arXiv:2609.30546v1 Announce Type: cross Abstract: In this paper, we establish the first asymptotic convergence guarantees for the Muon algorithm through a more accurate proxy for the Newton-Schultz it

arXiv:2609.31211v1 Announce Type: new Abstract: Underwater robotic inspection depends on acquiring views that reveal task-relevant structure. For a structurally complex coral colony, recognising the t

arXiv:2609.30275v1 Announce Type: new Abstract: A statistic reported without the quantity needed to interpret it is not evidence. We develop that thesis for a concrete practice in AI safety. Interpret

arXiv:2609.30360v1 Announce Type: cross Abstract: Inspired by the problem of identifying the best model from a collection of large language models (LLMs) with heterogeneous querying costs, we formulat

arXiv:2609.30811v1 Announce Type: new Abstract: Online conformal prediction can fail when predictions shape actions and actions determine which outcomes enter calibration. Standard adaptive methods ma

arXiv:2609.30974v1 Announce Type: new Abstract: Lexical semantic change is usually summarized by a scalar distance between independently sampled period distributions. This measures how much a word cha

arXiv:2609.30714v1 Announce Type: new Abstract: Agentic AI systems are increasingly being explored in medical imaging to improve throughput and reduce clinician workload; however, safe deployment rema

arXiv:2609.31149v1 Announce Type: new Abstract: Scientific measurements such as single-cell RNA (scRNA) sequencing often take the form of nonnegative integer counts, whereas continuous-state diffusion