Search: “reasoning”

arXiv:2607.05202v1 Announce Type: new Abstract: Agent self-evolution in long-horizon LLM systems is largely procedural: useful experience is not merely stored information, but reusable procedures for

arXiv:2607.02854v1 Announce Type: cross Abstract: Before fixing an issue, it is useful to first reproduce it by generating a bug reproduction test (BRT). However, generating a BRT is itself a challeng

Excellent investigation of the mechanics of language models. 🫢A notable blindspot, however: several teams have actually been **directly** comparing the working of LLMs to those of the human brain 🧠 fo

Chinese AI startup DeepSeek is developing its own inference chips to reduce Nvidia dependence and break U.S. export controls, as China moves to protect its AI ecosystem. DeepSeek has been quietly deve

arXiv:2607.04631v1 Announce Type: new Abstract: The cost of producing code is rapidly diminishing with increasingly capable AI agents, while quality assurance of generated programs has not kept pace.

arXiv:2607.03661v1 Announce Type: new Abstract: Point cloud-based understanding has become an important enabler for facility operation and maintenance involving indoor building components. However, ex

arXiv:2607.03789v1 Announce Type: new Abstract: Human spatial understanding arises from jointly perceiving geometry and semantics, enabling consistent object identification and localization across vie

arXiv:2607.04607v1 Announce Type: cross Abstract: The rapid advancement of AI-generated videos poses increasing security risks and calls for robust detectors with strong cross-domain generalization. A

arXiv:2607.04714v1 Announce Type: cross Abstract: Learning motion latents for robotic manipulation heavily relies on extracting motion patterns from visual sequences, yet effective action abstractions

arXiv:2607.02719v1 Announce Type: new Abstract: Radiologists routinely compare current and prior chest X-rays to track disease progression, producing follow-up reports that describe multiple findings,

arXiv:2607.05122v1 Announce Type: new Abstract: Vision-language-action (VLA) models enable robot navigation from natural language and visual goals, but remain susceptible to perceptual distractions an

arXiv:2607.03422v1 Announce Type: new Abstract: Recovering online pen trajectories from offline handwriting images, often referred to as handwriting trajectory recovery (stroke recovery), is an offlin

arXiv:2607.03155v1 Announce Type: new Abstract: The deployment of autonomous vehicles in urban environments introduces significant safety challenges, particularly in scenarios with occlusions, where c

If you care about AI, and want a nuanced view, you should watch this. I promise it will be worth your time. An excellent video from the @WorldSciFest featuring @GaryMarcus , in which he discusses—amon

arXiv:2607.02560v1 Announce Type: new Abstract: Pedestrian-level wind prediction is essential for urban design and wind-comfort assessment, but high-fidelity simulations such as LES remain computation

arXiv:2503.06643v2 Announce Type: replace-cross Abstract: In this paper, we tackle a critical challenge in model evaluation: how to keep code benchmarks useful when models might have already seen them

arXiv:2606.13156v2 Announce Type: replace-cross Abstract: Letting a vision-language model (VLM) think longer at test time has driven much recent progress. A natural way to bring this to spatial ground

arXiv:2504.20412v3 Announce Type: replace-cross Abstract: Fuzzing frameworks like syzkaller have uncovered thousands of Linux kernel crashes, many of which are critical and security-sensitive. However

arXiv:2602.08842v3 Announce Type: replace-cross Abstract: As highly automated driving is transitioning from single-vehicle closed-access testing to commercial deployments of public ride-hailing in sel

arXiv:2607.02609v1 Announce Type: cross Abstract: For decades, data engineering has developed mature architectural principles for integrating, governing, validating, cataloging, and serving organizati

arXiv:2607.05061v1 Announce Type: new Abstract: Key-value (KV) cache growth is a major bottleneck in autoregressive decoding, as memory and bandwidth scale linearly with context length. Existing KV ev

arXiv:2607.04352v1 Announce Type: new Abstract: In this work, we study the last-meter precision navigation for UAVs, e.g., autonomously reaching a target within the final 10 meters using monocular vis

arXiv:2607.05391v1 Announce Type: new Abstract: Scaling pre-training, post-training, and test-time compute have become the central paradigms for improving the capabilities of LLMs. In this work, we id

arXiv:2607.03651v1 Announce Type: new Abstract: While traditional hub capacity planning models optimize effectively for quantitative inputs, they often fail to digest qualitative business context. We

arXiv:2607.02703v1 Announce Type: cross Abstract: In this paper, we describe LLMoxie, an institutional AI platform whose three-tiered architecture supports multi-cloud and on-premise inference, a Lite

arXiv:2607.04648v1 Announce Type: cross Abstract: Depression screening from large-scale behavioral data is challenged by fragmented circadian indicators, limited interpretability, and the lack of inte

Karissa Bell / Engadget: Meta says Muse Image includes an invisible watermarking system called Content Seal and previews a web tool to check whether an image was generated with Meta AI — It has rate l

arXiv:2601.22054v2 Announce Type: replace-cross Abstract: Scaling has powered recent advances in vision foundation models, yet extending this paradigm to metric depth estimation remains challenging du

arXiv:2607.04763v1 Announce Type: cross Abstract: We study on-policy distillation (OPD) for agentic tasks, where an LLM agent interacts with an environment over multiple turns and a student imitates a

arXiv:2607.04371v1 Announce Type: new Abstract: We present Nemotron-Labs-3-Puzzle-75B-A9B, a compressed variant of Nemotron-3-Super optimized for interactive deployment. We designed the model to maxim

arXiv:2503.18509v2 Announce Type: replace Abstract: Weak supervision enables machine learning models to learn from limited or noisy labels, but it introduces challenges in reliability and semantic cla

arXiv:2607.03985v1 Announce Type: cross Abstract: Advanced neural technologies in speech synthesis and voice conversion (VC) have introduced severe risks to personal privacy, necessitating robust Spea

arXiv:2607.04537v1 Announce Type: cross Abstract: Code language models are now trusted collaborators in production workflows for debugging, refactoring, and iterative repair, and every benchmark that

arXiv:2607.05346v1 Announce Type: new Abstract: We propose OptiAgent, a multi-agent framework that, given a natural language description of an Operations Research problem, is able to output a solver-r

arXiv:2511.02200v2 Announce Type: replace Abstract: The emergence of multi-agent systems powered by large language models (LLMs) has unlocked new frontiers in complex task-solving, enabling diverse ag

arXiv:2607.02755v1 Announce Type: cross Abstract: Training AIs to be risk-averse in resources could offer a failsafe in the event that AIs turn out misaligned. Misaligned but risk-averse AIs would ten

arXiv:2607.02914v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated remarkable capabilities across diverse applications, yet ensuring their simultaneous safety, helpfulness,

arXiv:2607.04860v1 Announce Type: new Abstract: Gaze target estimation, the task of predicting where a person is looking in a scene, is crucial to understanding human attention and intent. It is a cha

arXiv:2607.03968v1 Announce Type: cross Abstract: Large language models are increasingly deployed as IDE-integrated coding agents that decompose tasks, generate and edit files, run code, and refine ou

arXiv:2607.02687v1 Announce Type: cross Abstract: Intrusion detection systems are often trained under static benchmark conditions, although deployed network environments are affected by traffic drift,

arXiv:2607.03058v1 Announce Type: new Abstract: Post-refinement can improve colonoscopy segmentation after host inference, but many designs still rely on extra correction heads or multi-stage pipeline

arXiv:2607.04364v1 Announce Type: new Abstract: Continual post-training is becoming a central paradigm for adapting vision-language models to evolving tasks. Recent work has increasingly favored reinf

arXiv:2607.03701v1 Announce Type: cross Abstract: Large language models (LLMs) can propose circuit-optimization decisions, but industrial analog flows cannot expose foundry PDK content, proprietary sc

arXiv:2607.03978v1 Announce Type: cross Abstract: Low-dimensional projections support interactive visual analysis of high-dimensional data embeddings, but their structure often does not align with ana

arXiv:2607.03883v1 Announce Type: new Abstract: The rapid advancement of deepfakes necessitates robust face forgery detection. Although forged faces may lack obvious artifacts, they often contain subt

This morning I released sqlite-utils 4.0, the 124th release of that project and the first major version bump since 3.0 in November 2020. In addition to some small but significant breaking changes (des