Knowledge catalogue
arXiv:2606.11447v1 Announce Type: new Abstract: Recent anecdotal evidence suggests that AI coding agents can reproduce published findings when provided with original data and code; yet systematic eval
arXiv:2606.11213v1 Announce Type: new Abstract: We present Context Window Lifecycle (CWL), a context-management scheme that gives long-horizon LLM agents an effectively unbounded working horizon. As a
arXiv:2606.12370v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become a key component in modern large language models, yet the rollout stage remains the key bottleneck in RL trainin
arXiv:2606.12109v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have demonstrated remarkable zero-shot generalization in robotic manipulation, yet the vast majority of pre-traine
By the way, public service announcement: if you're one of the numerous people posting about Anthropic's dystopian ways and you're thinking about getting Claude to help you write that post... don't! An
Can confirm we saw a strong spike in growth of token consumption for Codex over last 48 hours. Unusual when we don't launch something. Usage share of OpenAI grew vs Anthropic yesterday despite Mythos
arXiv:2606.12016v1 Announce Type: cross Abstract: Model post-training, and in particular reinforcement learning (RL), is one of the primary mechanisms by which developers can shape models' values and
arXiv:2606.11499v1 Announce Type: cross Abstract: The performance of modern language models depends critically on pretraining data composition. Yet existing data selection methods rely on auxiliary cl
arXiv:2606.12025v1 Announce Type: new Abstract: Finite element (FE) modeling of safety-critical infrastructure such as bridge barriers requires high-fidelity nonlinear dynamic analysis, yet the curren
arXiv:2606.11440v1 Announce Type: new Abstract: Existing multi-agent LLM orchestration methods, ranging from brute-force ensembles to learned routers, select models and topologies based on task and mo
arXiv:2606.12086v1 Announce Type: new Abstract: Contextualized assessment offers high ecological validity for evaluating creativity but introduces a critical challenge: observed performance may be con
arXiv:2606.12291v1 Announce Type: new Abstract: Large language models (LLMs) now reach expert-level scores on medical licensing exams, encouraging the assumption that high scores imply safe medical ju
arXiv:2506.02568v2 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated substantial efficacy in advancing graph-structured data analysis. Prevailing LLM-based graph methods
arXiv:2606.11946v1 Announce Type: cross Abstract: The conventional approach to deep learning over relational databases applies neural models, such as Graph Neural Networks (GNNs), to a graph represent
arXiv:2606.11897v1 Announce Type: new Abstract: Scientific discovery workflows usually contain and rely heavily on lab notes, where researchers record observations, interpret uncertain results, and pl
arXiv:2606.11680v1 Announce Type: new Abstract: Large language model (LLM) agents struggle with long-horizon tasks due to their inherent statelessness, requiring all task-relevant information to be en
arXiv:2511.13207v2 Announce Type: replace-cross Abstract: Object navigation in unseen indoor environments requires agents to perform semantic search under partial observability. Vision-language models
arXiv:2603.22934v3 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) improves large language model applications by grounding generation in retrieved evidence, but also introduces c
arXiv:2606.11574v1 Announce Type: new Abstract: In many materials and product design problems, desirable candidates exhibit properties that fall within an acceptable range rather than achieve a single
arXiv:2606.12250v1 Announce Type: new Abstract: Large language models (LLMs) in medicine are mainly evaluated using multiple-choice question answering (MCQA), which can overestimate real clinical abil
arXiv:2606.11860v1 Announce Type: new Abstract: In this paper, we introduce Representation Prediction via Autoencoding using Iterative Refinement (RePAIR) - a novel self-supervised representation lear
arXiv:2606.11512v1 Announce Type: new Abstract: Large language models increasingly express uncertainty through natural-language statements, yet these expressions often fail to reflect the model's samp
arXiv:2606.12374v1 Announce Type: cross Abstract: Effective multi-human-robot collaboration is essential for expanding human-led operations in the challenging and high-risk underwater environment. For
arXiv:2606.11552v1 Announce Type: new Abstract: Large language models (LLMs) achieve remarkable performance across a wide range of tasks, but their autoregressive decoding process incurs substantial i
arXiv:2409.18478v2 Announce Type: replace Abstract: With the development of video understanding, there is a proliferation of tasks for clip-level temporal video analysis, including temporal action det
arXiv:2512.11393v2 Announce Type: replace Abstract: Humans can intuitively parallelise complex activities, but can a model predict this from observing a single person? Given one egocentric video, we i
arXiv:2606.11437v1 Announce Type: cross Abstract: Efficiently sampling from a complex probability distribution is a fundamental problem which has become increasingly pertinent in recent years with the
arXiv:2509.23982v2 Announce Type: replace-cross Abstract: Preference alignment is a critical step in making Large Language Models (LLMs) useful and aligned with (human) preferences. Existing approache
arXiv:2606.11662v1 Announce Type: new Abstract: Deep search requires agents to answer complex questions through multi-step web search, browsing, evidence comparison, and synthesis. A central challenge
arXiv:2606.11265v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems are vulnerable to corpus poisoning attacks that manipulate downstream model outputs through malicious kno
arXiv:2606.11502v1 Announce Type: cross Abstract: Language models can state that 'the Earth orbits the Sun' and, when role-playing Aristotle, assert the opposite. Recent work argues that persona adopt
arXiv:2606.12072v1 Announce Type: new Abstract: Pretrained video generators are promising visual world models that exhibit emergent task-solving abilities; however, their reliance on detailed textual
arXiv:2606.11189v1 Announce Type: cross Abstract: Supervised fine-tuning (SFT) typically maximizes the likelihood of every token in a demonstrated trajectory. However, an observed token can be non-uni
arXiv:2606.11150v1 Announce Type: new Abstract: Large language models (LLMs) are rapidly acquiring capabilities relevant to biological research, from literature synthesis to interpretation of experime
arXiv:2606.10787v1 Announce Type: new Abstract: Neurosymbolic AI combines neural networks with symbolic programs to create robust and explainable predictions. One such framework is NeurASP, which trai
arXiv:2606.10525v1 Announce Type: cross Abstract: Indirect prompt injection poses a critical threat to LLM agents that interact with untrusted external data, yet automated attack methods--proven effec
arXiv:2505.23851v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly applied to symbolic mathematics, yet existing evaluations often conflate pattern memorization wi
arXiv:2606.10156v1 Announce Type: cross Abstract: As recommender systems transition toward agentic, multi-turn conversational interfaces, evaluation paradigms have struggled to keep pace. Current benc
arXiv:2606.10064v1 Announce Type: cross Abstract: Small-model agentic post-training is bottlenecked less by the algorithm than by the trajectory substrate it consumes. Leading recipes (RLVR, group-rel
arXiv:2606.10808v1 Announce Type: new Abstract: Multi-pair robotic assembly in unstructured environments faces spatial interference and contact uncertainties. Existing paradigms fail to bridge cogniti
arXiv:2606.10044v1 Announce Type: new Abstract: Businesses are increasingly adopting AI-enabled tools to improve productivity, reduce costs, and enhance products and services. However, the transformat
arXiv:2509.19936v2 Announce Type: replace Abstract: Human gaze estimation is essential for applications such as human-computer interaction, social robotics, and assistive systems. However, achieving a
arXiv:2511.02603v2 Announce Type: replace Abstract: Large language models (LLMs) are often queried multiple times at test time, with predictions aggregated by majority vote. While effective, this self
arXiv:2606.10087v1 Announce Type: new Abstract: Pre-training on raw code teaches syntax but provides sparse signal for diverse real-world task formats. While synthetic data has proven transformative f
Coding agents break when models are 'almost' bug-free. But almost valid JSON is just not the same valid JSON. Fun piece here from @akshay_pachaar shows why SFT can't fix this, and how GRPO trains agai
arXiv:2606.10328v1 Announce Type: cross Abstract: The integration of spatial and spectral information is beneficial to the improvement of change detection performance. However, existing methods cannot
arXiv:2606.09957v1 Announce Type: cross Abstract: Semantic faults specific to the use of machine learning models are a common problem for machine learning developers, causing suboptimal predictions, h
arXiv:2606.11176v1 Announce Type: cross Abstract: Data tells stories that shape society; the data journalist's job is to turn raw information into stories non-experts can trust. A high-quality news fe
arXiv:2606.10400v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly deployed where answers must follow from what is in the image, yet they often answer from textual priors,
arXiv:2606.10799v1 Announce Type: new Abstract: Large Language Models (LLMs) struggle to rigorously verify complex mathematical proofs. Standard global evaluation approaches suffer from 'context poiso
Everyone Operating At The Frontier Satya Nadella, Chairman & CEO, Microsoft, interviewed by @saranormous & @eladgil (No Priors) and @swyx (Latent Space) Crossover special at Microsoft Build 2026. Summ
arXiv:2606.10208v1 Announce Type: cross Abstract: Demand for older-adult and patient care is growing rapidly as populations age worldwide. Foundation models are increasingly being integrated into robo
arXiv:2606.10468v1 Announce Type: new Abstract: Coastline detection in remote sensing imagery is commonly formulated as a pixel-wise segmentation problem, where the final coastline is extracted from a
arXiv:2606.10602v1 Announce Type: new Abstract: Precise rover localization is a prerequisite for autonomous lunar exploration, yet the absence of Global Navigation Satellite System (GNSS) signals and
arXiv:2601.18765v2 Announce Type: replace Abstract: Autonomous robotic systems are widely deployed in smart factories and operate in dynamic, uncertain, and human-involved environments that require lo
arXiv:2606.09635v1 Announce Type: cross Abstract: Ensuring the reliability of Large Language Models (LLMs) under distribution drift requires inference-time adaptation. While inference-time alignment m
arXiv:2606.10743v1 Announce Type: new Abstract: Learning from human video demonstrations remains challenging due to noisy hand-object interactions, unseen objects with partial observation, and cross-e
arXiv:2606.10839v1 Announce Type: new Abstract: Current identity-consistent video generation methods struggle to preserve appearance fidelity under large viewpoint changes. While introducing multi-vie
arXiv:2606.10507v1 Announce Type: new Abstract: While Large Language Models (LLMs) have demonstrated strong capabilities as autonomous agents across a wide range of tasks, their performance often degr
arXiv:2606.09908v1 Announce Type: cross Abstract: Large language models (LLMs) are becoming widely deployed as personal AI assistants with access to sensitive user data, making privacy a major challen