Knowledge catalogue
arXiv:2608.16391v1 Announce Type: cross Abstract: As large language models become increasingly widespread, third-party providers that deploy open-weight models have become an important part of the eco
arXiv:2608.15260v1 Announce Type: cross Abstract: Maintaining global geometric consistency is a central challenge in long-sequence 3D reconstruction, with scale drift being the most critical failure m
arXiv:2608.16572v1 Announce Type: new Abstract: Learning from demonstration is a promising approach for dexterous manipulation, but collecting high-quality contact-critical demonstrations remains diff
arXiv:2506.01584v2 Announce Type: replace-cross Abstract: Developing machine learning (ML) systems for real-world deployment requires navigating context-dependent trade-offs among accuracy, fairness,
arXiv:2608.15392v1 Announce Type: new Abstract: Chain-of-thought monitoring is a potentially useful safety signal, but its reliability across languages and behavioral settings remains uncertain. In a
arXiv:2608.16428v1 Announce Type: cross Abstract: Artificial intelligence systems often disclose uncertainty, yet they rarely make clear what response that uncertainty should trigger. Most uncertainty
We have paused some frontier RL training to ensure that we can meet the appropriate alignment, security and monitoring standards for the new level of capabilities in front of us. Model progress is now
We’re sharing the concrete changes we’re making to strengthen monitoring, security, and alignment as capabilities advance. We’ve introduced stronger workload and network isolation, continuous security
arXiv:2608.16801v1 Announce Type: new Abstract: We study how teams of AI coding agents coordinate while solving programming tasks. Current evaluations usually report whether the agents complete the ta
arXiv:2608.15338v1 Announce Type: cross Abstract: Sentiment classifiers are increasingly applied to social media content that is either sarcastic or AI-generated --- two distributional regimes where s
arXiv:2608.16515v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) improves large language models by grounding generation in external evidence, but it also introduces a source trus
arXiv:2608.15323v1 Announce Type: new Abstract: Understanding a model and its learning mechanisms in depth requires identifying when its internal structures become useful, rather than simply looking a
arXiv:2608.16627v1 Announce Type: cross Abstract: Natural language explanations (NLEs) are increasingly used as inputs, for example, as few-shot rationales that influence model behavior in in-context
arXiv:2608.16806v1 Announce Type: cross Abstract: Large Language Models (LLMs) have demonstrated capabilities in in-context learning, task decomposition, step-by-step reasoning, and code generation, d
arXiv:2608.14886v1 Announce Type: new Abstract: Retrieval quality in RAG systems is commonly reported as a single aggregate score, which can hide large differences across query types and language cond
arXiv:2608.15530v1 Announce Type: new Abstract: Reinforcement learning with human feedback (RLHF) aligns LLMs with human preferences, improving summarization fluency and safety, but causes sentiment d
arXiv:2608.15085v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) exhibit substantial performance degradation in non-English visual reasoning, despite the strong multilingual co
arXiv:2608.15641v1 Announce Type: new Abstract: This paper evaluates Wiktionary as an ethically crowdsourced lexicon for English dialects. We took a two-phase approach, providing an in-depth descripti
arXiv:2602.14344v2 Announce Type: replace-cross Abstract: We study instruction following in multi-task reinforcement learning, where an agent must zero-shot execute novel tasks not seen during trainin
arXiv:2608.16590v1 Announce Type: new Abstract: Embodied agents are increasingly used to close the gap left by end-to-end policy models. Yet the agentic path has not realized closed-loop learning in p
arXiv:2603.07571v3 Announce Type: replace-cross Abstract: Out-of-distribution (OOD) detection is critical in safety-sensitive applications. While this challenge has been addressed from various perspec
arXiv:2608.14239v1 Announce Type: cross Abstract: Operating teams of autonomous aircraft in dynamic, uncertain, and potentially adversarial environments requires safety protocols that are reliable yet
arXiv:2608.14038v1 Announce Type: new Abstract: Modern text-to-image diffusion models rely on classifier-free guidance (CFG) to achieve high image fidelity and text alignment. However, CFG typically a
arXiv:2608.14135v1 Announce Type: cross Abstract: Autonomous pursuit-evasion is a fundamental challenge for Unmanned Aerial Vehicles (UAVs), requiring rapid decision-making under tightly coupled dynam
arXiv:2608.14130v1 Announce Type: cross Abstract: Computer vision models for generated facial content, such as face editing and privacy protection, increasingly affect people, requiring similarity met
arXiv:2608.13760v1 Announce Type: cross Abstract: Which reasoning behaviors are associated with correct answers in reasoning models, and does reasoning-oriented training amplify those behaviors? This
arXiv:2608.13752v1 Announce Type: cross Abstract: Modern transmission electron microscopes are versatile instruments which have become indispensable tools for understanding structure and chemical comp
arXiv:2608.13840v1 Announce Type: cross Abstract: Audits of generative AI (GenAI) systems often summarize behavior as a reported rate: how often the audited system complies with policy. Researchers an
arXiv:2602.09430v2 Announce Type: replace-cross Abstract: Robotic laboratories play a critical role in autonomous scientific discovery by enabling scalable, continuous experimental execution. Recent v
arXiv:2608.13918v1 Announce Type: new Abstract: Long-range vision-based deformation monitoring is highly sensitive to motion of the camera platform. Absolute-pose differencing typically relies on dedi
arXiv:2608.14043v1 Announce Type: new Abstract: Diffusion Transformers (DiTs) have become the dominant paradigm for high-fidelity video generation, yet their ability to perform high-level semantic pla
arXiv:2608.14161v1 Announce Type: new Abstract: LLMs exhibit social biases that can produce inaccurate and discriminatory inferences, posing risks in high-stakes applications. While prior work has mad
arXiv:2603.18871v2 Announce Type: replace Abstract: Urban Vehicular Ad-Hoc Networks (VANETs) can become fragmented because buildings obstruct wireless links and vehicle mobility continuously changes t
arXiv:2603.28026v2 Announce Type: replace Abstract: Multimodal multiple-choice question answering (MCQA) provides a standardized and objectively measurable setting for evaluating vision-language model
arXiv:2608.13925v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) accelerate language generation by predicting multiple masks in a single forward pass. However, existing dLLMs
arXiv:2608.14339v1 Announce Type: new Abstract: We study proactive exploration in LLM agents, i.e., the ability to explore an environment to acquire information that improves future decision-making. I
arXiv:2608.13939v1 Announce Type: cross Abstract: Ultrasound is the primary imaging modality for assessing thyroid nodules, and the ACR TI-RADS framework standardizes diagnosis through five ultrasound
arXiv:2505.19196v2 Announce Type: replace Abstract: Recent advances in text-to-image (T2I) diffusion model fine-tuning leverage reinforcement learning (RL) to align generated images with learnable rew
arXiv:2608.13651v1 Announce Type: cross Abstract: We solve exactly a fundamental problem of adaptive control against adversarial disturbances: regulate the scalar system x_{t+1} = ax_t + u_t + w_t, x_
arXiv:2608.14448v1 Announce Type: new Abstract: Autonomous racecars operate at the limits of vehicle dynamics, where small control errors translate into safety-critical behavior and lost performance.
arXiv:2608.14332v1 Announce Type: cross Abstract: Reinforcement learning is promising for autonomous urban driving, but long-horizon goal-directed navigation asks a policy to acquire several competing
arXiv:2607.28336v3 Announce Type: replace Abstract: On-policy distillation provides dense supervision for multimodal reasoners, but its trajectory-level reward cannot determine whether a failed answer
arXiv:2608.14011v1 Announce Type: cross Abstract: Generative recommendation autoregressively generates the semantic IDs of the target item, unifying preference modeling and index retrieval within the
arXiv:2608.14481v1 Announce Type: cross Abstract: As heterogeneous robotic systems deploy across diverse urban zones, maintaining safety amid complex human-robot interactions remains a critical challe
arXiv:2608.13754v1 Announce Type: new Abstract: The EU AI Act requires providers of high-risk systems to file technical documentation describing how the system reaches its decisions. Mechanistic inter
arXiv:2311.07073v3 Announce Type: replace Abstract: Graph-based message-passing neural networks (MPNNs) have achieved remarkable success in both node and graph-level learning tasks. However, several i
arXiv:2608.13681v1 Announce Type: cross Abstract: Translating C code into safe, idiomatic Rust is a longstanding software-engineering goal because it can eliminate entire classes of memory-safety vuln
arXiv:2608.14022v1 Announce Type: cross Abstract: Action-conditioned video world models require low-latency causal generation and reliable responses to game-native controls. Although causal distillati
arXiv:2608.13741v1 Announce Type: new Abstract: Synthesizing time series from natural language is emerging as the most expressive form of controllable time series generation. However, existing text-co
arXiv:2608.13698v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR), often optimized with Group Relative Policy Optimization (GRPO), has become a central recipe for i
hilarious the way people are now pretending that the tech ceos never promised us AGI Anthropic CEO Dario Amodei: — There is a 'good chance' that AGI could be built within the next 1 - 3 years. — There
arXiv:2608.13617v1 Announce Type: new Abstract: Verifying whether clinical care follows evidence-based protocols is a natural neuro-symbolic problem, yet the safety-critical setting defeats either par
arXiv:2204.13805v5 Announce Type: replace-cross Abstract: Gender gaps in how scientific work is evaluated are well documented, but their sources remain debated. We ask whether an overlooked factor---t
arXiv:2608.13878v1 Announce Type: new Abstract: In mixed traffic, decision-making for autonomous vehicles (AVs) confronts three interrelated challenges. First, physics-based priors incorporated into r
arXiv:2608.13695v1 Announce Type: cross Abstract: Large language model providers routinely cite multilingual safety benchmarks spanning a dozen or more languages as evidence that their models are safe
arXiv:2608.14114v1 Announce Type: new Abstract: As the integration of volatile renewable energy sources increases the strain on modern power grids, the use of Reinforcement Learning (RL) for autonomou
arXiv:2608.13624v1 Announce Type: cross Abstract: Large Audio Language Models (LALMs) have seen increasing use for audio understanding tasks such as speech recognition and audio question answering, ra
arXiv:2608.13911v1 Announce Type: new Abstract: Federated multimodal medical AI faces modality heterogeneity at both the client and sample levels: clients may systematically lack access to specific mo
arXiv:2608.13690v1 Announce Type: cross Abstract: Medical image segmentation is still largely treated as a vision-only problem, although clinical interpretation often relies on textual knowledge of an
arXiv:2608.14198v1 Announce Type: cross Abstract: Banks analyse sequential financial transaction data to perform many tasks, including fraud prevention, credit risk assessment and offer personalizatio