Knowledge catalogue
arXiv:2605.26554v1 Announce Type: cross Abstract: Contextual dueling bandits form a cornerstone of preference-based decision-making, with critical applications in recommender systems and large languag
arXiv:2605.26710v1 Announce Type: new Abstract: The distance at which a mobile robot reacts to a person strongly impacts various qualities of the human-robot interaction. In this paper, we focus on th
arXiv:2605.27186v1 Announce Type: new Abstract: Large language models often solve tasks from a fully specified prompt but degrade when the same requirements unfold over multiple turns, known as the lo
arXiv:2605.27345v1 Announce Type: new Abstract: Reliable evaluation is essential for understanding large language model (LLM) performance, yet today's go-to metrics, namely token-overlap scores (e.g.,
arXiv:2605.26726v1 Announce Type: cross Abstract: Neural cellular automata (NCA) provide a lightweight alternative to encoder-decoder segmentation networks. However, it can be difficult to decide when
arXiv:2605.26343v1 Announce Type: new Abstract: Mechanistic interpretability has identified small sets of attention heads that implement specific behaviours in transformer language models, but recover
arXiv:2605.26154v1 Announce Type: cross Abstract: LLM-driven agents are capable of selecting external tools to complete users' tasks. However, attackers could compromise such process, steering agents
🚨 MICHAEL BURRY WARNS THREE UPCOMING IPOs COULD COMPLETELY CRASH THE STOCK MARKET. Michael Burry reported that the upcoming public listings for SpaceX, OpenAI, and Anthropic are going to pull more cap
arXiv:2605.27097v1 Announce Type: new Abstract: The successful training of neural networks hinges on the use of first order optimization methods, yet the theoretical characterization of these methods
arXiv:2603.25415v2 Announce Type: replace Abstract: Semantic world models enable embodied agents to reason about objects, relations, and spatial context beyond purely geometric representations. In Org
arXiv:2510.06381v2 Announce Type: replace-cross Abstract: We propose Monte Carlo Permutation Search (MCPS), a general-purpose Monte Carlo Tree Search (MCTS) algorithm that improves upon the GRAVE algo
More CEOs saying the obvious. AI has been hyped so much over the last few years that every other technology, market trend, and idea is overlooked. When will be get past the mania about imminent AGI, c
arXiv:2605.26878v1 Announce Type: new Abstract: Multi-stakeholder tasks require one output to satisfy users with conflicting preferences. Holistic LLM judges conflate utility estimation and utility ag
arXiv:2602.09878v2 Announce Type: replace Abstract: World-model-based imagine-then-act becomes a promising paradigm for robotic manipulation, yet existing approaches typically support either purely im
arXiv:2605.26942v1 Announce Type: new Abstract: LLMs deployed in high-stakes domains face fundamental reliability challenges: hallucinations, inconsistencies, and privacy vulnerabilities introduce una
arXiv:2602.10104v2 Announce Type: replace-cross Abstract: Scaling action-controllable world models is limited by the scarcity of action labels. While latent action learning promises to extract control
arXiv:2605.26162v1 Announce Type: cross Abstract: Asynchronous decentralized federated learning (ADFL) eliminates central coordination and global synchronization, making it attractive for large-scale
arXiv:2605.26194v1 Announce Type: new Abstract: Clinical time-series learning is routinely constrained by small, heterogeneous cohorts and protocol drift, while its downstream use spans both classific
Only thing completely clear about the future of work is that Altman and Amodei will say whatever they think will drive up their IPOs. Altman and Amodei have said for years that AI was so powerful that
arXiv:2605.26526v1 Announce Type: new Abstract: Recent defenses for safeguarding open-weight large language models (LLMs) are intended to prevent adversarial usage. Underlying these defenses is an ass
Maria Curi / Axios: OpenAI announces partnerships to combat election misinformation, offering cybersecurity products to state officials and backing legislation to curb deepfakes — OpenAI is announcing
arXiv:2602.00827v2 Announce Type: replace Abstract: Feature learning strength (FLS), i.e., the inverse of the effective output scaling of a model, plays a critical role in shaping the optimization dyn
arXiv:2605.27255v1 Announce Type: cross Abstract: Long chain-of-thought reasoning has made autoregressive decoding the dominant inference cost of modern large language models. Existing methods target
Palantir CEO Alex Karp goes after AI slop. The fight over AI “slop” is really a fight over whether software is performing or merely pretending. 'The appearance of software working is not software work
Gary Marcus deleted an original post after Gergely Orosz provided comments questioning the compelling nature of the data presented. The post appears to have been withdrawn due to critical feedback tha
arXiv:2507.16679v3 Announce Type: replace-cross Abstract: In-Context Learning has shown great potential for aligning Large Language Models (LLMs) with human values, helping reduce harmful outputs and
arXiv:2602.04990v3 Announce Type: replace Abstract: The allocation of scarce donor organs constitutes one of the most consequential algorithmic challenges in healthcare. While the field is rapidly tra
arXiv:2605.26903v1 Announce Type: cross Abstract: Structured data is well handled by gradient-boosted decision trees (GBDT), which are usually trained on vertically partitioned features across mutuall
arXiv:2605.26625v1 Announce Type: new Abstract: We present a provably safe sampling-based motion planning algorithm for robotic systems affected by random disturbances of unknown distribution. We cons
arXiv:2508.02806v3 Announce Type: replace Abstract: Recently, a significant improvement in the accuracy of 3D human pose estimation has been achieved by combining convolutional neural networks (CNNs)
arXiv:2605.26266v1 Announce Type: cross Abstract: Chunk-wise autoregressive video diffusion models rely on a KV cache of previously generated chunks to avoid redundant computation, but this cache quic
arXiv:2605.27315v1 Announce Type: new Abstract: Visual inputs are often assumed to improve language understanding in multimodal models. We examine this assumption by asking whether vision-language mod
arXiv:2605.27014v1 Announce Type: cross Abstract: Large Language Models (LLMs) have transformed artificial intelligence from primarily generative systems into increasingly capable reasoning agents. Re
arXiv:2602.04879v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has become a cornerstone for fine-tuning Large Language Models (LLMs), with Proximal Policy Optimization (PPO) ser
arXiv:2605.26441v1 Announce Type: cross Abstract: This paper addresses the challenging task of weakly-supervised video temporal grounding. Existing approaches are generally based on the moment proposa
arXiv:2605.26352v1 Announce Type: new Abstract: Retrieval is increasingly moving from one-shot matching toward interactive reasoning, where language agents iteratively inspect evidence, reformulate qu
arXiv:2605.26452v1 Announce Type: cross Abstract: Safe reinforcement learning (RL) for robotic systems requires policies that improve task performance while satisfying state and input constraints duri
arXiv:2605.26640v1 Announce Type: cross Abstract: We study the sample complexity of policy gradient for log-growth control -- the problem of learning, from observed state transitions, a feedback gain
arXiv:2605.26282v1 Announce Type: new Abstract: Model-based reinforcement learning (RL) can be effectively supported at scale through the use of world models. However, in practice, scaling such approa
arXiv:2605.27009v1 Announce Type: new Abstract: Predicting human olfactory perception from molecular structure has seen remarkable progress, yet these approaches require explicit chemical structure at
arXiv:2605.27032v1 Announce Type: new Abstract: Accurate pancreas segmentation is critical for early cancer diagnosis, where annotation scarcity necessitates Semi-Supervised Learning (SSL). However, d
arXiv:2510.19420v2 Announce Type: replace-cross Abstract: Multi-Agent Systems (MAS) have become a prevalent paradigm for Large Language Model (LLM) applications. However, the complex multi-agent desig
arXiv:2605.26690v1 Announce Type: cross Abstract: Protein sequence optimization under tight oracle budgets requires methods that explore vast combinatorial spaces while making each evaluation informat
arXiv:2605.27155v1 Announce Type: cross Abstract: Testing object detectors in safety-critical domains requires semantically meaningful probes beyond pixel-level corruptions. We present SemProbe, a too
arXiv:2605.26973v1 Announce Type: cross Abstract: Neural networks are known to develop latent representations that are aligned, namely structurally similar across networks trained with different archi
arXiv:2512.14140v2 Announce Type: replace Abstract: Sketch editing requires jointly handling high-level semantic changes and precise local redrawing, a combination that is particularly challenging for
arXiv:2605.26704v1 Announce Type: cross Abstract: Epidemic forecasting faces a fundamental challenge: human behavior dynamically responds to disease spread, creating feedback loops that induce distrib
some data i shared yesterday on anthropic revenue possibly slowing down aren’t as a compelling as i thought; i have deleted my posts and await better data before drawing conclusions. h/t @GergelyOrosz
arXiv:2506.08543v3 Announce Type: replace Abstract: High-level representations have become a central focus in enhancing AI transparency and control, shifting attention from individual neurons or circu
arXiv:2605.26606v1 Announce Type: cross Abstract: Reinforcement learning (RL) is the dominant paradigm for post-training large language models. However, in the online, on-policy setting, rollout gener
arXiv:2605.27027v1 Announce Type: new Abstract: The scaling of quantum processors is currently limited by technical challenges such as decoherence and cross-talk. As the number of qubits grows, interf
Starbucks learned the hard way: you literally can’t even trust (current) AI to count. For some reason OpenAI doesn’t seem to be talking about how Starbucks spent years creating and testing an AI inven
arXiv:2605.27140v1 Announce Type: new Abstract: Reinforcement learning for multi-turn agents suffers from a credit-assignment mismatch: rewards are sparse and trajectory-level, while success often hin
arXiv:2602.04599v2 Announce Type: replace Abstract: We propose stochastic decision horizons (SDH), a theoretically grounded framework for solving constrained RL problems with every-step constraint sat
arXiv:2601.05729v2 Announce Type: replace Abstract: Recent studies have demonstrated the efficacy of integrating Group Relative Policy Optimization (GRPO) into flow matching models, particularly for t
arXiv:2601.07085v2 Announce Type: replace-cross Abstract: Large language model (LLM)-based conversational AI systems present a challenge to human cognition that current frameworks for understanding mi
arXiv:2605.27220v1 Announce Type: new Abstract: In modern RAG pipelines, query augmentation methods such as HyDE and query expansion are applied to every query, resulting in substantial LLM inference
arXiv:2605.26670v1 Announce Type: cross Abstract: Sequential editing of structured knowledge in large language models allows targeted factual updates without retraining, yet existing methods often rel
arXiv:2605.26415v1 Announce Type: cross Abstract: Deploying Vision-Language Models on resource-constrained hardware typically requires INT8 quantization, but in joint-embedding architectures such as C
arXiv:2605.27163v1 Announce Type: new Abstract: In strategic classification, an institution (e.g., a bank) anticipates adaptation from users who change their features to increase utility in a classifi