Knowledge catalogue
arXiv:2604.15695v1 Announce Type: cross Abstract: Cooperative equilibria are fragile. When agents learn alongside each other rather than in a fixed environment, the process of learning destabilizes th
arXiv:2604.16042v1 Announce Type: cross Abstract: While Large Language Models (LLMs) have achieved strong performance across many NLP tasks, their opaque internal mechanisms hinder trustworthiness and
arXiv:2604.15705v1 Announce Type: new Abstract: Reinforcement Fine-Tuning (RFT) has established itself as a critical paradigm for the alignment of Multi-modal Large Language Models (MLLMs) with comple
arXiv:2604.15507v1 Announce Type: new Abstract: Planning safe trajectories under model uncertainty is a fundamental challenge. Robust planning ensures safety by considering worst-case realizations, ye
arXiv:2510.04237v5 Announce Type: replace Abstract: In this paper, we propose a novel kernel stochastic gradient descent (SGD) algorithm for large-scale supervised learning with general losses. Compar
arXiv:2603.05719v2 Announce Type: replace Abstract: Training machine learning models for radioisotope identification using gamma spectroscopy remains an elusive challenge for many practical applicatio
arXiv:2604.15827v1 Announce Type: cross Abstract: Conventional information retrieval is concerned with identifying the relevance of texts for a given query. Yet, the conventional definition of relevan
arXiv:2604.15938v1 Announce Type: new Abstract: Diffusion policies are becoming mainstream in robotic manipulation but suffer from hard negative class imbalance due to uniform sampling and lack of sam
arXiv:2506.02261v3 Announce Type: replace-cross Abstract: What enables large language models (LLMs) to effectively model user preferences in sequential recommendation? Our investigation reveals that e
arXiv:2510.09689v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have been augmented with web search to overcome the limitations of the static knowledge boundary by accessing up-
arXiv:2601.03746v3 Announce Type: replace Abstract: As large language models (LLMs) are more frequently used in retrieval-augmented generation pipelines, it is increasingly relevant to study their beh
arXiv:2604.15738v1 Announce Type: new Abstract: Chromatic Correlation Clustering (CCC) extends Correlation Clustering by assigning semantic colors to edges and requiring each cluster to receive a sing
arXiv:2408.15549v4 Announce Type: replace Abstract: As large language models (LLMs) continue to advance, aligning these models with human preferences has emerged as a critical challenge. Traditional a
arXiv:2604.15762v1 Announce Type: new Abstract: Large-scale Unmanned Aerial Vehicle (UAV) failures can split an unmanned aerial vehicle swarm network into disconnected sub-networks, making decentraliz
Gary Marcus critiques the assumption that massive financial investment in AI scaling alone can solve fundamental challenges related to common sense reasoning in artificial intelligence systems. The po
Anthony Ha / TechCrunch: Tesla expands its robotaxi service to Dallas and Houston after launching in Austin last year and starting to offer rides without safety drivers in January 2026 — Tesla is expa
Gary Marcus argues that Dario Amodei (Anthropic CEO) and Sam Altman (OpenAI CEO) share more similarities in their approaches to AI development and safety than commonly perceived, despite their public
easyaligner is a forced alignment library designed to be performant and easy to use , leveraging GPU acceleration to align audio with text transcriptions. The tool supports flexible text normalization
EVERYONE who heard about @SeismicOrg (Seismic Foundation)'s report that AI 'salience' is low NEEDS to hear about this! New research from data science wiz @davidshor shows AI is now ahead of ABORTION a
Is a 92% “honest”* AI really good enough? Or a disaster waiting to happen? —- *”honest” is itself a misleading anthropomorphization of the kind Anthropic loves to promote. “Accurate” would be more acc
“my honest read is that a significant portion of this spending is driven by competitive fear rather than demonstrated returns. Nobody wants to be the company that didn't invest in AI when everyone els
arXiv:2604.14722v1 Announce Type: new Abstract: Transformers commonly exhibit an attention sink: disproportionately high attention to the first position. We study this behavior in GPT-2-style models w
arXiv:2604.15289v1 Announce Type: new Abstract: In recent years, reinforcement learning (RL) has shown remarkable success in robotics when a fast and accurate simulator is available for a given task.
arXiv:2510.01433v2 Announce Type: replace Abstract: Vision-based robot learning often relies on dense image or point-cloud inputs, which are computationally heavy and entangle irrelevant background fe
arXiv:2604.14534v1 Announce Type: new Abstract: Purpose. Athlete monitoring is constrained by small cohorts, heterogeneous biomarker scales, limited feasibility of repeated sampling, and the lack of r
arXiv:2509.05367v4 Announce Type: replace-cross Abstract: Large Language Model safety alignment predominantly operates on a binary assumption that requests are either safe or unsafe. This classificati
arXiv:2604.14895v1 Announce Type: new Abstract: We propose a new perspective on policy optimization: rather than reweighting all samples by their importance ratios, an optimizer should select which sa
arXiv:2604.14460v1 Announce Type: cross Abstract: Neuromotor decoding from upper-limb electromyography (sEMG) can enhance human-machine interfaces and offer a more natural means of controlling prosthe
arXiv:2602.07069v2 Announce Type: replace Abstract: Powered by multimodal text-to-image priors, diffusion-based super-resolution excels at synthesizing intricate details; however, models trained on sy
arXiv:2604.15124v1 Announce Type: new Abstract: Continuous glucose monitoring (CGM) is central to diabetes care, but explaining CGM patterns clearly and empathetically remains time-intensive. Evidence
arXiv:2510.20151v2 Announce Type: replace Abstract: Structured texts refer to texts containing structured elements beyond plain texts, such as code snippets and placeholders. Such structured texts inc
arXiv:2604.13101v1 Announce Type: cross Abstract: The integration of Large Language Models (LLMs) into aviation safety decision-making represents a significant technological advancement, yet their sta
arXiv:2604.14251v1 Announce Type: new Abstract: Monitoring LLM safety at scale requires balancing cost and accuracy: a cheap latent-space probe can screen every input, but hard cases should be escalat
arXiv:2604.14961v1 Announce Type: new Abstract: Contextual bandit algorithms suffer from high regret during cold-start, when the learner has insufficient data to distinguish good arms from bad. We pro
arXiv:2604.14892v1 Announce Type: new Abstract: Evaluating medical AI systems using expert clinician panels is costly and slow, motivating the use of large language models (LLMs) as alternative adjudi
arXiv:2604.14520v1 Announce Type: new Abstract: Omni-modal Large Language Models (Omni-MLLMs) promise a unified integration of diverse sensory streams. However, recent evaluations reveal a critical pe
arXiv:2604.14856v1 Announce Type: new Abstract: Understanding climate change requires reasoning over complex causal networks. Yet, existing causal discovery datasets predominantly capture explicit, di
arXiv:2604.14612v1 Announce Type: cross Abstract: Self-speculative decoding is an inference technique for large language models designed to speed up generation without sacrificing output quality. It c
arXiv:2603.02196v2 Announce Type: replace-cross Abstract: An agent must try new behaviors to explore and improve. In high-stakes environments, an agent that violates safety constraints may cause harm
arXiv:2604.15224v1 Announce Type: cross Abstract: The extit{LLM-as-a-judge} paradigm has become the operational backbone of automated AI evaluation pipelines, yet rests on an unverified assumption: th
arXiv:2602.06930v2 Announce Type: replace Abstract: We study off-policy reinforcement learning for controlling continuous-time Markov diffusion processes with discrete-time observations and actions. W
arXiv:2604.14556v1 Announce Type: new Abstract: Video object insertion is a critical task for dynamically inserting new objects into existing environments. Previous video generation methods focus prim
arXiv:2604.15267v1 Announce Type: cross Abstract: It is increasingly important that LLM agents interact effectively and safely with other goal-pursuing agents, yet, recent works report the opposite tr
arXiv:2604.14449v1 Announce Type: new Abstract: Recent advances in data-centric artificial intelligence highlight inherent limitations in object recognition datasets. One of the primary issues stems f
arXiv:2604.14651v1 Announce Type: new Abstract: Clinical language models (LMs) are increasingly applied to support clinical risk prediction from free-text notes, yet their uncertainty estimates often
arXiv:2506.13763v2 Announce Type: replace-cross Abstract: Diffusion models have achieved remarkable success in generative modeling. Despite more stable training, the loss of diffusion models is not in
arXiv:2411.00361v4 Announce Type: replace Abstract: Hierarchical reinforcement learning (HRL) enables agents to solve complex, long-horizon tasks by decomposing them into manageable sub-tasks. However
arXiv:2510.26109v4 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) has significantly boosted the reasoning capability of language models (LMs). However, existing
arXiv:2604.15023v1 Announce Type: new Abstract: Mobile manipulation is a fundamental capability that enables robots to interact in expansive environments such as homes and factories. Most existing app
arXiv:2603.25903v2 Announce Type: replace Abstract: Scaling robot learning to long-horizon tasks remains a formidable challenge. While end-to-end policies often lack the structural priors needed for e
arXiv:2604.13959v1 Announce Type: new Abstract: As AI moves from data centers to robots and wearables, scaling ever-larger models becomes insufficient. Physical AI operates under tight latency, energy
arXiv:2604.14267v1 Announce Type: new Abstract: Search agents extend Large Language Models (LLMs) beyond static parametric knowledge by enabling access to up-to-date and long-tail information unavaila
Everyone’s quitting but everything’s going great. AGI will be here next week. Scout’s honor! This story has now been updated with more details. Three leaders departed from OpenAI today: - Kevin Weil,
arXiv:2604.13151v1 Announce Type: new Abstract: Language Model (LM) agents are increasingly used in complex open-ended decision-making tasks, from AI coding to physical AI. A core requirement in these
arXiv:2604.14459v1 Announce Type: new Abstract: For humans, filler-gap dependencies require a shared representation across different syntactic constructions. Although causal analyses suggest this may
arXiv:2510.02738v3 Announce Type: replace-cross Abstract: While visuomotor policy has made advancements in recent years, contact-rich tasks still remain a challenge. Robotic manipulation tasks that re
arXiv:2510.14133v2 Announce Type: replace Abstract: Agentic AI systems, which leverage multiple autonomous agents and large language models (LLMs), are increasingly used to address complex, multi-step
arXiv:2604.14805v1 Announce Type: new Abstract: Grain-edge segmentation (GES) and lithology semantic segmentation (LSS) are two pivotal tasks for quantifying rock fabric and composition. However, thes
arXiv:2604.03920v2 Announce Type: replace Abstract: LLM-based social simulations can generate believable community interactions, enabling ``policy wind tunnels'' where governance interventions are tes
arXiv:2604.14583v1 Announce Type: new Abstract: Decentralized Finance (DeFi) lending protocols like Aave v3 rely on over-collateralization to secure loans, yet users frequently face liquidation due to