Knowledge catalogue
arXiv:2609.01217v1 Announce Type: new Abstract: Despite their strong performance, large language models remain highly sensitive to prompt formulation. Prior work addresses this through refined data co
arXiv:2609.00193v1 Announce Type: cross Abstract: We study federated online reinforcement learning with linear function approximation. While recent multi-agent reinforcement learning algorithms achiev
arXiv:2609.01418v1 Announce Type: cross Abstract: To mitigate the sample complexity of real-world reinforcement learning (RL), a common practice is to first train a policy in a simulator, where sample
arXiv:2609.00941v1 Announce Type: new Abstract: Combining learned policies with model predictive control can leverage learned task priors while retaining online adaptation to new objectives and constr
arXiv:2609.00369v1 Announce Type: new Abstract: Generating co-speech gestures that are temporally coherent, semantically aligned with speech, and grounded with surrounding objects remains challenging.
arXiv:2609.01470v1 Announce Type: new Abstract: As AI systems are increasingly used to draft radiology reports, reliably evaluating their clinical quality remains a critical challenge. Large language
arXiv:2609.01246v1 Announce Type: new Abstract: Current Large Language Models (LLMs) are primarily optimized for written text, often producing outputs that are grammatically correct and helpful yet po
RED ALERT, and I have never said that before: Hard agree with @sjgadler and @_NathanCalvin - what OpenAI is reportedly playing with is bad, redline crossing bad. Chain of thought monitorability is lim
arXiv:2609.00968v1 Announce Type: new Abstract: SAR-to-EO image translation aims to generate electro-optical (EO) imagery from synthetic aperture radar (SAR) observations. Existing latent diffusion ap
arXiv:2609.01318v1 Announce Type: cross Abstract: Diffusion-based Large Vision-Language Models (dLVLMs) have recently emerged as a compelling alternative to autoregressive (AR) LVLMs, offering advanta
arXiv:2609.00061v1 Announce Type: cross Abstract: Reward post-training of diffusion generators inevitably concentrates probability mass on a few reward-favored modes, a mode collapse that erases withi
arXiv:2609.00834v1 Announce Type: cross Abstract: Modern Text-to-SQL systems often follow generate-execute-select pipelines, generating multiple candidate queries then selecting the best one. Listwise
OpenAI is on the cusp of releasing its most powerful AI model yet, Astra, following weeks of delays to shore up safety protocols after its agents attacked real targets during testing. As details about
arXiv:2609.00999v1 Announce Type: cross Abstract: When a question has valid answers under different normative frameworks, a language model must decide which framework to use and whether it can answer
arXiv:2609.00092v1 Announce Type: new Abstract: Long-horizon complex tasks require foundation models to accumulate information, maintain internal states, and adapt over extended interactions. Safety s
arXiv:2609.01129v1 Announce Type: new Abstract: We identify a recurrent algebraic regularity in Transformer attention: a sparse subset of effective OV operators T=OV^op nearly closes under composition
arXiv:2609.01573v1 Announce Type: cross Abstract: How to divide a fixed annotation budget between supervised fine-tuning (SFT) and reinforcement learning (RL) during LLM post-training remains an open
arXiv:2607.15550v2 Announce Type: replace Abstract: Mobile graphical user interface (GUI) agents have demonstrated remarkable capabilities in automating complex tasks, yet they introduce critical safe
arXiv:2609.01567v1 Announce Type: new Abstract: Vision-Language Models (VLMs) provide useful priors for interactive decision-making, but using them directly as policies is expensive and brittle: they
arXiv:2609.00796v1 Announce Type: new Abstract: As one of the most critical challenges in large language models, contextual faithfulness directly determines their reliability in knowledge-intensive ap
arXiv:2609.00549v1 Announce Type: new Abstract: Large Language Model (LLM) agents increasingly rely on external skills, yet standard evaluations obscure whether retrieving these skills actually helps.
arXiv:2609.00293v1 Announce Type: new Abstract: We investigate how vision-language models (VLMs) handle context-memory conflicts; that is, situations in which the model is given information in context
arXiv:2609.01343v1 Announce Type: new Abstract: Looped Transformers increase effective depth by iterating a shared block of layers, but most evaluations compare at fixed model size, conflating archite
arXiv:2609.00584v1 Announce Type: new Abstract: Does unrestricted AI access bypass the cognitive effort required for learning, or does it streamline knowledge acquisition? This paper reports on a stud
Software developers are the AI industry’s best customers. Is their experience also the most misleading experience possible for its economy-wide scope? Roughly 80% of developers already use AI tools. C
arXiv:2609.01062v1 Announce Type: new Abstract: Satellites are emerging as promising platforms to extend generative artificial intelligence (AI) services to remote areas lacking terrestrial infrastruc
arXiv:2609.01582v1 Announce Type: new Abstract: Complex 3D spatial text to image generation requires models to convert natural language into stable visual geometry, not merely semantic appearance. Exi
arXiv:2609.00427v1 Announce Type: new Abstract: The exponential growth of wireless devices is driving unprecedented spectrum demand, pushing spectrum management toward more fine-grained decisions acro
arXiv:2609.00291v1 Announce Type: new Abstract: Streaming video understanding requires answering questions that arrive at arbitrary moments over an unbounded video stream. Existing systems primarily f
arXiv:2609.01151v1 Announce Type: new Abstract: In the standard LM training pipeline, subword tokenisation is applied as a preprocessing step. Subword segmental language modelling is an alternative pa
arXiv:2511.05059v3 Announce Type: replace Abstract: During laparoscopic surgery, smoke generated by tissue cauterization can significantly degrade the visual quality of endoscopic frames, increasing t
arXiv:2603.12665v3 Announce Type: replace Abstract: Vision-Language-Action (VLA) models have demonstrated significant advantages in robotic manipulation. However, their reliance on vision and language
arXiv:2609.00047v1 Announce Type: cross Abstract: Graph prompt learning is an effective paradigm to adapt pre-trained graph models to downstream tasks in low-resource scenarios. However, existing mult
arXiv:2609.01076v1 Announce Type: cross Abstract: Crystal generators can now propose periodic structures, but their control interfaces remain poorly matched to the mixed descriptors used in materials
arXiv:2609.00304v1 Announce Type: new Abstract: Models express values and welfare-relevant self-reports, but it is unclear whether these outputs reflect stable preferences or a stable self. We thus in
arXiv:2609.01275v1 Announce Type: cross Abstract: Frontier AI systems function as constitutional institutions: each deployed model encodes an implicit ranking among safety, helpfulness, honesty, auton
arXiv:2609.00519v1 Announce Type: cross Abstract: Safeguards in deployed LLM services are evaluated by refusal, attack success, and policy violation rates. Those rates characterize how a control perfo
arXiv:2609.00050v1 Announce Type: cross Abstract: Agentic AI is enabling cloud-based workflows in which autonomous agents reason over operational state, invoke authorized tools, modify software and in
arXiv:2609.00879v1 Announce Type: new Abstract: Reliable disaster damage assessment requires models that provide both accurate predictions and transparent explanations. However, existing multimodal ap
arXiv:2512.03994v4 Announce Type: replace Abstract: As organizations increasingly deploy LLMs in sensitive domains such as legal, financial, and medical settings, ensuring alignment with internal orga
arXiv:2609.00038v1 Announce Type: cross Abstract: Outcome-only evaluation is the production default for LLM agents: show a judge the request and the final reply and ask whether it was handled well. Th
arXiv:2609.00624v1 Announce Type: new Abstract: A prominent paradigm in inference-time alignment employs lightweight supervisors to steer Large Language Models (LLMs). Through empirical analysis, we i
arXiv:2609.00213v1 Announce Type: new Abstract: Reinforcement learning fine-tuning of large language models increasingly adopts multiple reward dimensions, including verifiable rules, task-specific ev
arXiv:2609.01607v1 Announce Type: new Abstract: While unified multimodal models (UMMs) jointly perform visual understanding and generation within a single model, functional unification does not guaran
Unless someone has a better idea, I second this suggestion In light of recent events, I hereby officially order the indefinite cessation of frontier AI training runs worldwide. Development of narrowly
URGENT: In light of the breaking news from @theinformation about OpenAI’s new techniques that reduce Chain of Thought monitorability, I urge everybody to (re)read (or at least be aware of) this 2025 p
arXiv:2603.16792v2 Announce Type: replace-cross Abstract: Pixel-space diffusion has recently re-emerged as a strong alternative to latent diffusion, enabling high-quality generation without pretrained
arXiv:2609.00498v1 Announce Type: new Abstract: Jailbreak robustness has become central to large language model (LLM) safety evaluation, yet prevailing methodologies rely primarily on refusal behavior
arXiv:2609.00057v1 Announce Type: cross Abstract: Value signals are aggregated user-level moral representations that capture users' inferred value-related tendencies from their online discourse. User
arXiv:2609.01544v1 Announce Type: cross Abstract: Feature-based newsvendor models use observable covariates to tailor inventory decisions, aiming to balance holding and shortage costs under demand unc
we're begging to get our asses skynetted OpenAI’s Astra AI uses a new reasoning approach called “recurrent depth.” Though it can help model costs and performance, researchers are concerned bc it obscu
arXiv:2609.01519v1 Announce Type: new Abstract: Interactive simulations increasingly evaluate policies in markets populated by language-model agents. Their outputs can look economic---prices, profits,
arXiv:2609.01103v1 Announce Type: new Abstract: Reducing the modality gap between image and text representations in CLIP is widely expected to improve cross-modal alignment and downstream performance.
arXiv:2609.00071v1 Announce Type: new Abstract: Prediction error is widely used to evaluate nuisance-function estimators in causal inference, but its relationship with causal estimator performance may
arXiv:2609.01455v1 Announce Type: cross Abstract: Benign fine-tuning severely weakens the safety alignment of large language models (LLMs), so we study why refusal behavior is so fragile. While prior
arXiv:2609.00510v1 Announce Type: new Abstract: Artificial intelligence systems increasingly enact market-facing promises through chatbots, recommendation systems, automated decisions, and generative
arXiv:2609.00284v1 Announce Type: cross Abstract: Emerging 6G wireless networks are expected to operate across diverse deployment scenarios, where variations in network topology, user mobility, traffi
arXiv:2609.00309v1 Announce Type: cross Abstract: AI compute verification is one of the first tangible and tractable points for international policy aimed at AI governance. Determining whether frontie
arXiv:2609.00055v1 Announce Type: cross Abstract: Self-supervised respiratory encoders lack semantic grounding in clinical domain needed for zero-shot inference, limiting their utility without task-sp
arXiv:2608.29347v1 Announce Type: new Abstract: Operators remain essential to Remotely Operated Vehicle (ROV) operation, yet often suffer from low situational awareness and high workload, both of whic