Search: “context”

arXiv:2606.29340v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) trains a reasoning model on rollouts sampled from its own policy by matching a privileged teacher that also sees veri

arXiv:2601.12033v2 Announce Type: replace Abstract: Quantization is widely adopted to reduce the computational cost of large language models (LLMs); however, its implications for fairness and safety,

arXiv:2606.30291v1 Announce Type: new Abstract: Text-Attributed Graphs (TAGs) combine textual semantics with graph structure and are central to many graph learning tasks. However, existing fusion meth

arXiv:2606.30133v1 Announce Type: cross Abstract: Retrieval-augmented generation built on knowledge graphs (Graph RAG) outperforms flat passage retrieval on multi-hop question answering by leveraging

arXiv:2606.18112v3 Announce Type: replace-cross Abstract: Agentic navigation systems require a base navigation model whose observation strategy can be externally reconfigured at inference time, becaus

arXiv:2606.29937v1 Announce Type: new Abstract: Understanding how users perceive and respond to robot failures is essential for building robust and trustworthy robot systems. Prior work, however, (i)

arXiv:2606.28649v1 Announce Type: cross Abstract: We present RIPA, the first systematic multi-channel empirical study of prompt injection attacks delivered through the sensory pipeline of a ROS 2-base

arXiv:2606.20515v2 Announce Type: replace Abstract: Real-world spatial intelligence requires reasoning over a continuous and evolving 3D world, yet existing VLMs and tool-augmented agents largely rema

arXiv:2606.30393v1 Announce Type: new Abstract: Photographs frequently contain visual distractors besides foregrounds and backgrounds of the intended subject, competing for attention and weakening com

arXiv:2606.29520v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used as assistants across the software development lifecycle, yet their ability to reason about software

arXiv:2606.29942v1 Announce Type: new Abstract: Anticipation of human behaviours facilitates autonomous systems in proactive planning. Human behaviour could be stochastic due to varying goals. Human g

arXiv:2606.28715v1 Announce Type: cross Abstract: While AI development and evaluation for Southeast Asia (SEA) has grown rapidly, agent capabilities in regional languages are still poorly understood d

arXiv:2606.30244v1 Announce Type: new Abstract: Referring Remote Sensing Image Segmentation (RRSIS) seeks to localize and segment the target object or region specified by a natural language expression

arXiv:2606.28389v1 Announce Type: new Abstract: We present our submission to the SoccerNet 2026 Player-Centric Ball Action Spotting challenge, which uses a two-stage pipeline: a Track-Aware Action Det

arXiv:2506.20771v2 Announce Type: replace Abstract: We propose a latent score-based generative AI framework for learning stochastic, non-local closure models and constitutive laws in nonlinear dynamic

arXiv:2606.29247v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models represent a promising direction for embodied intelligence in surgical robotics. Despite the prevalence of VLA benchm

arXiv:2606.29423v1 Announce Type: new Abstract: The importance of gesture recognition has been acknowledged in many domains requiring real-time recognition systems. Two requirements for these are fast

arXiv:2512.17151v2 Announce Type: replace Abstract: We present a framework for document-centric background generation with multi-page editing and thematic continuity. To ensure text regions remain rea

arXiv:2606.29799v1 Announce Type: new Abstract: This project introduces the CRISTAL Method (Coherent Reliable Intentional Synthesis of Truthful Analysis Logic), a neurosymbolic framework for automatin

The food delivery leader in China just dropped an open weights 1.6 trillion parameter model while half the USA was sleeping … 🫨 🇨🇳 Meituan, China's largest food delivery platform, open-sourced a 1.6 t

arXiv:2606.29832v1 Announce Type: new Abstract: Machine unlearning aims to eliminate the influence of specific data from trained models to safeguard privacy. However, this presents a significant chall

arXiv:2606.28327v1 Announce Type: cross Abstract: How do retrieval bounds compare between human episodic memory and Retrieval-Augmented Generation (RAG) systems under semantic interference? We present

Thrilled to announce the Wearable AI Workshop at ECCV 2026 🎉 that we're organizing with an awesome group of folks across Meta Reality Labs, AMI Labs, HKUST, Georgia Tech, UCF, and U. of Edinburgh. If

arXiv:2602.23294v2 Announce Type: replace Abstract: In real scenarios, videos can span several minutes or even hours. However, existing research on spatio-temporal video grounding (STVG), given a text

arXiv:2606.30560v1 Announce Type: cross Abstract: Coding agents are rapidly becoming a major application of agentic LLMs, but serving them efficiently remains challenging. Progress on this challenge r

arXiv:2606.28659v1 Announce Type: cross Abstract: High-fidelity molecular docking simulations can produce biologically relevant estimates of epitope-receptor binding affinity but are computationally e

arXiv:2606.29502v1 Announce Type: new Abstract: Skill memories can improve agentic reinforcement learning by reusing past experience as textual guidance, but retrieved skills are not oracular: they ma

arXiv:2606.29781v1 Announce Type: new Abstract: Urban building change detection from bi-temporal aerial imagery is important for redevelopment monitoring, infrastructure management, and unauthorized-c

arXiv:2601.03546v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used to simulate decision-making tasks involving personal data sharing, where privacy concerns a

Watch Devin Fusion work: The sidekick model handles fetching information and skimming sources. The frontier model makes a plan for implementation, then delegates well-scoped sub-tasks to the sidekick

This post discusses loop constructs and control flow mechanisms in programming, likely covering concepts such as for loops, while loops, and their practical applications. Based on Swyx's typical conte

What an honor to emcee the first day of @aiDotEngineer and introduce the Software Factories Track Thank you @swyx & team, and @KeycardLabs for the support. “A year ago @GeoffreyHuntley released the Ra

What's new in Claude Sonnet 5 Claude Sonnet 5 came out this morning. I always head straight for the 'what's new' developer docs because they tend to have more actionable information than the official

arXiv:2603.15389v2 Announce Type: replace Abstract: Recent work has demonstrated the curse of depth in large language models (LLMs), where later layers contribute less to learning and representation t

arXiv:2606.28544v1 Announce Type: cross Abstract: Team roles offer an interpretable lens on collaboration, yet computational studies of roles often rely on domain-specific personas or data-driven clus

arXiv:2606.30587v1 Announce Type: cross Abstract: Researchers and practitioners increasingly apply Large Language Models (LLMs) for automated vulnerability detection. Recent work has shown that LLMs a

arXiv:2606.28758v1 Announce Type: cross Abstract: Predicting future states is essential for autonomous agents, yet current Vision-Language-Action (VLA) models fundamentally lack this capability, relyi

arXiv:2606.27881v1 Announce Type: cross Abstract: Temporal variation poses a unique challenge for named entity recognition (NER) in historical texts, where entities drift in surface form and salience

arXiv:2405.19466v4 Announce Type: replace Abstract: We pose uncertainty quantification and exploration in online decision-making as a problem of training and generation from an autoregressive sequence

arXiv:2606.13544v3 Announce Type: replace-cross Abstract: Turn-taking in multi-party spoken conversations remains a fundamental challenge for voice-based agents, particularly under dynamic floor compe

arXiv:2606.27685v1 Announce Type: cross Abstract: Pervasive data contamination -- stemming from measurement errors, outliers, or adversarial corruption -- has motivated the development of robust stati

arXiv:2506.01442v2 Announce Type: replace Abstract: Reinforcement learning (RL) remains fundamentally limited by poor data efficiency and weak generalization. Prior episodic RL methods attempt to alle

arXiv:2606.27500v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) specialized in healthcare are emerging as a promising research direction due to their potential impact in clinica

arXiv:2604.00784v2 Announce Type: replace Abstract: Surgical video understanding is a crucial prerequisite for advancing Computer-Assisted Surgery. While vision-language models (VLMs) have recently be

This post likely discusses using the Mythos release or announcement as a reference point for calculating timelines or milestones related to an AI project or product. Without access to the specific twe

arXiv:2606.28186v1 Announce Type: cross Abstract: Predicting human item difficulty is central to educational assessment, where reliable estimates support fairness and effective test construction. Exis