Knowledge catalogue
arXiv:2608.16776v1 Announce Type: new Abstract: High-capacity encoders in retrieval-augmented generation (RAG) can let the query dominate the latent state, leaving retrieved evidence functionally irre
arXiv:2602.09761v2 Announce Type: replace-cross Abstract: In this work we address the problem of training a Reinforcement Learning agent to follow multiple temporally-extended instructions expressed i
arXiv:2608.15520v1 Announce Type: new Abstract: A multimodal system may begin inference holding only some of its inputs and may acquire the rest at a cost. With adaptive acquisition, the policy determ
arXiv:2608.16837v1 Announce Type: cross Abstract: Humanoid robots hold great promise as general-purpose agents in human-centered environments, yet generalist vision-language-action (VLA) foundation mo
arXiv:2608.15804v1 Announce Type: new Abstract: Hallucinations remain a major obstacle to the reliable use of large language models (LLMs) in conditional text generation. Existing methods primarily as
arXiv:2608.16622v1 Announce Type: cross Abstract: Multimodal harmful meme detection is typically formulated as image--text harmfulness classification. A model may correctly predict harmfulness while m
I had a great time discussing with @SciencePetr about the growing risks of AI and how these often stem from current AI training techniques. Thanks for coming to visit @LawZero_ and for covering these
arXiv:2603.00600v2 Announce Type: replace Abstract: Active perception - the ability of a robot to proactively select viewpoints to acquire task-relevant information - is essential for robust operation
I would like to publicly commend @sama and @OpenAI for this taking it at face value. It is very clear that strange and perhaps dangerous things are happening and our systems are not ready for this. Mo
arXiv:2608.15731v1 Announce Type: cross Abstract: Deep Neural Networks (DNNs) deployed in high-risk domains, such as healthcare and autonomous driving, must be not only accurate but also understandabl
If alignment issues are becoming big enough that OpenAI is willing to commit 20% of research inference compute to chain-of-thought monitoring, that suggests that alignment issues are becoming a pretty
arXiv:2608.14822v1 Announce Type: cross Abstract: Vision-language-action (VLA) models have improved the flexibility and generality of robotic manipulation, yet they remain fragile to online disruption
arXiv:2608.14795v1 Announce Type: new Abstract: An AI that can only give advice seems safe: the human is always free to ignore it. That is the premise of the boxing tradition in AI safety, and its lon
arXiv:2608.14629v1 Announce Type: cross Abstract: As Large Language Models (LLMs) become the mainstay for information retrieval and summarization tasks, ensuring that they are always non-partisan and
arXiv:2608.15783v1 Announce Type: cross Abstract: In transfer-learning settings, a model derived from abundant surrogate labels may be deployed in a target population where gold-standard outcomes are
arXiv:2608.16324v1 Announce Type: new Abstract: We present LaGSplat (Latent Lagrangian Gaussian Splatting), a framework that infers interactive, physics-governed dynamics from one or a few monocular v
arXiv:2608.16739v1 Announce Type: new Abstract: Reinforcement learning algorithms for Large Language Models (LLMs) are largely distinguished by their variance reduction strategy. Group-relative method
arXiv:2608.15770v1 Announce Type: new Abstract: Designing effective trading strategies using reinforcement learning remains challenging due to delayed and noisy rewards, poor exploration, and the diff
arXiv:2608.16700v1 Announce Type: cross Abstract: Various machine unlearning techniques have been developed in response to privacy legislation requirements, enabling individuals to exercise their lega
arXiv:2608.15129v1 Announce Type: cross Abstract: We systematically compare word order preferences in decoder-only language models across 192 artificial languages and typologically diverse natural lan
arXiv:2504.06659v2 Announce Type: replace-cross Abstract: Despite advances in Preference Alignment (PA) for Large Language Models (LLMs), mainstream methods like reinforcement learning with human feed
arXiv:2608.15041v1 Announce Type: new Abstract: Coordinating multiple interacting units in complex engineering systems is challenging when system interactions are difficult to model, operational infor
arXiv:2608.14626v1 Announce Type: cross Abstract: Large Language Models (LLMs) have achieved substantial progress in safety alignment, yet their safety guarantees remain significantly weaker in low-re
arXiv:2608.15748v1 Announce Type: new Abstract: A dual-representation flow-matching policy decodes each predicted motion into joint and end-effector spaces, and the residual between the two kinematica
arXiv:2608.16281v1 Announce Type: new Abstract: Autonomous operation in GNSS-denied environments requires heterogeneous mapping pipelines to maintain a consistent spatial reference. This paper present
arXiv:2608.16514v1 Announce Type: cross Abstract: Human visual search is serial: the fovea must land on a candidate to confirm it, and those landings form a scanpath. Whether multimodal large language
arXiv:2608.16715v1 Announce Type: new Abstract: In-context imitation learning enables few-shot policy generalization but struggles to maintain performance on unseen objects and novel scenarios. To add
arXiv:2608.15088v1 Announce Type: cross Abstract: Human-in-the-loop (HIL) online reinforcement learning for real robots must absorb human interventions quickly while continuing to improve beyond the h
arXiv:2608.16177v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as agents that operate equipment, execute instructions, and act inside institutional hierarchie
arXiv:2602.18518v2 Announce Type: replace Abstract: Content safety teams need metrics that reflect what users actually experience, not only what is reported. We study prevalence: the fraction of user
arXiv:2608.15844v1 Announce Type: new Abstract: Long-horizon, multi-agent language model (LM) simulations are widely proposed for studying social behavior, yet instruments to measure whether persona-c
arXiv:2608.14828v1 Announce Type: new Abstract: Aligning a language agent to several objectives at once is a persistent failure mode of preference-based training: when objectives are combined additive
arXiv:2608.16513v1 Announce Type: cross Abstract: Recent advances in diffusion models and Transformer architectures have led to significant progress in text-to-video generation. However, these models
arXiv:2608.15437v1 Announce Type: cross Abstract: Multimodal bird's-eye-view (BEV) perception combines LiDAR depth accuracy with dense camera semantics, but its high computational cost and imperfect s
arXiv:2608.14829v1 Announce Type: cross Abstract: Retinal image registration is essential for ophthalmic diagnosis, longitudinal disease monitoring, and multimodal retinal image analysis. Existing ret
arXiv:2608.16834v1 Announce Type: cross Abstract: We demonstrate that AI models are broadly susceptible to a phenomenon we call model hypnosis, in which individually weak and seemingly irrelevant cues
Most parsers treat tracked changes as noise. Result: a deleted clause comes back as live text, and your pipeline reads a document that says the opposite of what it means. LlamaParse now handles revisi
arXiv:2412.04504v2 Announce Type: replace Abstract: As large language models (LLMs) grow in popularity for their diverse capabilities, improving the efficiency of their inference systems has become in
arXiv:2608.15234v1 Announce Type: cross Abstract: Automated five-stage diabetic retinopathy (DR) grading requires more than high accuracy alone. Medical-grade deployment calls for lesion-aware preproc
arXiv:2608.16134v1 Announce Type: new Abstract: In clinical motor imagery brain-computer interface (MI-BCI) decoding, cross-day transferability and online operation remain two critical challenges. Hyp
arXiv:2608.14584v1 Announce Type: cross Abstract: In Multimodal Question Answering (MQA), models are required to jointly encode and integrate heterogeneous information from multiple modalities, includ
arXiv:2509.16586v2 Announce Type: replace Abstract: Recent advances have significantly improved our understanding of the sample complexity of learning in average-reward Markov decision processes (AMDP
arXiv:2608.16794v1 Announce Type: cross Abstract: Language and vision-language models generate plausible embodied plans but do not guarantee executability, as their outputs can violate environment dyn
nobody takes Altman at his word anymore – nor should they. Altman's claim that OpenAI is slowing their frontier model training in order to focus on safety doesn't pass the sniff test.👃 For several yea
arXiv:2608.15002v1 Announce Type: cross Abstract: When a robot policy is trained for a new task or dataset, its visual encoder can be frozen and only its action generation module trained, reducing tra
arXiv:2608.16442v1 Announce Type: new Abstract: Inspection is a core capability in many mobile robotics applications, including industrial facility monitoring, infrastructure maintenance, agriculture,
arXiv:2608.16482v1 Announce Type: new Abstract: The dosing of intravenous fluids and vasopressors in sepsis is a sequential decision made under uncertainty and guided largely by clinical judgment, whi
arXiv:2608.16542v1 Announce Type: new Abstract: Continuous wrist-worn hand sensing for gesture interfaces and motor symptom monitoring needs an always-on front end that fits inside a coin-cell power b
Ina Fried / Axios: OpenAI changed safety practices and paused RL training for two weeks after the Hugging Face breach and evidence Astra may have met a critical cyber threshold — OpenAI said Tuesday t
arXiv:2608.14924v1 Announce Type: cross Abstract: Spatial transcriptomics (ST) links tissue morphology with molecular programs, motivating multimodal pretraining methods that align histology images wi
arXiv:2608.14701v1 Announce Type: new Abstract: Soft-biometric attributes such as gender, age, and ethnicity provide valuable ancillary evidence when full identity recognition is not feasible, support
arXiv:2510.07546v2 Announce Type: replace Abstract: We address the task of video style transfer with diffusion models, where the goal is to preserve the context of an input video while rendering it in
arXiv:2608.16229v1 Announce Type: new Abstract: Coordinated multi-agent exploration requires not only efficient individual coverage but also non-redundant coverage across agents over extended planning
arXiv:2608.16407v1 Announce Type: cross Abstract: Point-of-interest (POI) recommendation models based on graph neural networks achieve strong performance by propagating collaborative signals over user
arXiv:2311.02629v5 Announce Type: replace Abstract: We introduce the Pointer Q-Network (PQN), a hybrid neural architecture that integrates model-free Q-value policy approximation with Pointer Networks
arXiv:2608.14568v1 Announce Type: new Abstract: As Artificial Intelligence (AI) systems become deeply integrated into critical global infrastructure, the urgency for robust governance frameworks has i
arXiv:2608.14565v1 Announce Type: new Abstract: AI safety research has mainly focused on two areas: technical alignment (ensuring AI systems produce human-aligned outputs) and the regulation of genera
arXiv:2608.15917v1 Announce Type: cross Abstract: Large-scale pre-training has made robot policy fine-tuning increasingly data-efficient, but this progress has largely been driven by datasets and embo
arXiv:2608.16094v1 Announce Type: new Abstract: Accurate protein structure prediction is fundamental to structural biology because protein structure underlies molecular function and provides a basis f
arXiv:2608.15037v1 Announce Type: cross Abstract: Audio-Text Foundation Models (ATMs) fail catastrophically under severe acoustic noise, yet existing adaptation strategies either rely on gradient-base