Metropolis-Adjusted Diffusion Models
arXiv:2605.09654v1 Announce Type: cross Abstract: Sampling from score-based diffusion models incurs bias due to both time discretisation and the approximation of the score function. A common strategy
Knowledge catalogue
arXiv:2605.09654v1 Announce Type: cross Abstract: Sampling from score-based diffusion models incurs bias due to both time discretisation and the approximation of the score function. A common strategy
arXiv:2605.08472v1 Announce Type: new Abstract: The effectiveness of Reinforcement Learning (RL) in Large Language Models (LLMs) depends on the nature and diversity of the data used before and during
arXiv:2604.02438v2 Announce Type: replace Abstract: The deployment of reinforcement learning (RL)-based controllers on physical systems is often limited by poor generalization to real-world scenarios,
arXiv:2605.09258v1 Announce Type: cross Abstract: Accurate hand and finger tracking from video has significant clinical applications for monitoring activities of daily living and measuring range of mo
arXiv:2510.26067v2 Announce Type: replace Abstract: Tensegrity robots combine rigid rods and elastic cables, offering high resilience and deployability but at the same time posing major challenges for
arXiv:2605.10177v1 Announce Type: cross Abstract: Robust urban autonomous driving requires reliable 3D scene understanding and stable decision-making under dense interactions. However, existing end-to
arXiv:2605.10494v1 Announce Type: cross Abstract: Probing heads map the representations learned from audio by a machine learning model to downstream task labels and are a key component in evaluating r
arXiv:2605.09364v1 Announce Type: new Abstract: This paper investigates robust representation learning in offline goal-conditioned reinforcement learning (GCRL). Particularly in sparse reward scenario
arXiv:2508.17497v2 Announce Type: replace-cross Abstract: Multimodal representation learning has been largely driven by contrastive models such as CLIP, which learn a shared embedding space by alignin
arXiv:2511.07833v3 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has become a standard recipe for post-training LLMs on reasoning tasks, with Group Relat
arXiv:2605.09672v1 Announce Type: new Abstract: State-of-the-art 6-DoF grasp generators excel on tabletop benchmarks with overhead cameras but struggle in frontal grasping scenarios on low-cost manipu
arXiv:2605.10671v1 Announce Type: new Abstract: In this work, we show that natural policy gradient, a core algorithm in reinforcement learning, admits an exact formulation as a smoothed and averaged f
In this post, we show you how to set up FLOPs tracking during LLM fine-tuning using the open source Fine-Tuning FLOPs Meter toolkit on Amazon SageMaker AI. You learn how to determine your compliance s
arXiv:2605.09176v1 Announce Type: cross Abstract: Training large language models requires optimization algorithms that are not only statistically effective, but also computationally and memory efficie
arXiv:2510.05635v2 Announce Type: replace-cross Abstract: Test-Time Adaptation (TTA) methods are often computationally expensive, require a large amount of data for effective adaptation, or are brittl
arXiv:2605.10877v1 Announce Type: new Abstract: Automated question answering (QA) over electronic health records (EHRs) demands precise evidence retrieval, faithful answer generation, and explicit gro
arXiv:2605.05373v2 Announce Type: replace Abstract: A key capability of intelligent agents is operating under partial observability: reasoning and acting effectively despite missing or incomplete stat
arXiv:2605.09595v1 Announce Type: cross Abstract: Reinforcement learning (RL) has enabled robust quadruped locomotion over complex terrain, but most learned controllers are trained offline with backpr
not every day @scaling01 and I agree. but he’s right. and most people won’t notice it happening, per the work of @informor. hot take: unrestricted LLMs are as dangerous as weapons of mass destruction
Gary Marcus references a conversation with someone named Haider, noting that despite Haider's typically optimistic outlook, he has shared documented evidence of expressing concerns about a particular
arXiv:2602.06382v2 Announce Type: replace Abstract: Achieving robust vision-based humanoid locomotion remains challenging due to two fundamental issues: the sim-to-real gap introduces significant perc
arXiv:2605.09433v1 Announce Type: new Abstract: Existing preference datasets for text-to-image models typically store only the final winner/loser images. This representation is insufficient for rectif
arXiv:2605.09725v1 Announce Type: new Abstract: On-policy distillation (OPD), which supervises a student on its own sampled trajectories, has emerged as a data-efficient post-training method for impro
arXiv:2605.09606v1 Announce Type: cross Abstract: Recent advances in image-to-3D models have significantly improved the fidelity and accessibility of 3D content creation. Such a powerful reconstructio
arXiv:2605.09235v1 Announce Type: cross Abstract: One-step generative modeling has emerged as a leading approach to amortize the inference cost of diffusion and flow-matching models. Among distillatio
arXiv:2605.09184v1 Announce Type: new Abstract: We present Open Ontologies, an open-source ontology engineering system implemented in Rust that integrates LLM-driven construction with formal OWL reaso
Sam Altman's personal investments faced increased scrutiny from Republican lawmakers following reporting by The Wall Street Journal in April regarding potential conflicts of interest. The controversy
arXiv:2603.10165v2 Announce Type: replace-cross Abstract: Every agent interaction generates a next-state signal, namely the user reply, tool output, terminal or GUI state change that follows each acti
Opinion: It is rare for the US public to agree on anything these days. Fear of AI is as close to a national consensus as it gets. A clear majority says that AI will do more harm than good. https://ft.
arXiv:2605.09640v1 Announce Type: new Abstract: Recent studies suggest that Reinforcement Fine-Tuning (RFT) is inherently more resilient to catastrophic forgetting than Supervised Fine-Tuning (SFT). H
arXiv:2605.08253v1 Announce Type: cross Abstract: Distributional reinforcement learning (DRL) models the full return distribution, but existing finite-support or quantile-based methods rely on project
arXiv:2602.23161v2 Announce Type: replace Abstract: Time series reasoning demands both the perception of complex dynamics and logical depth. However, existing LLM-based approaches exhibit two limitati
Pay attention to this one if you build research or knowledge-work agents. Most research-agent systems produce uniform outputs regardless of who is driving them. This new work, NanoResearch, argues tha
arXiv:2605.09422v1 Announce Type: new Abstract: Although Large Multimodal Models (LMMs) have achieved strong performance on general video understanding, their susceptibility to textual prior shortcuts
arXiv:2605.10043v1 Announce Type: cross Abstract: Large Language Model (LLM) personalization aims to align model behaviors with individual user preferences. Existing methods often focus on isolated us
arXiv:2605.10137v1 Announce Type: cross Abstract: Thompson sampling is a widely used strategy for contextual bandits: at each round, it samples a reward function from a Bayesian posterior and acts gre
arXiv:2605.10073v1 Announce Type: new Abstract: Patent claims form a directed dependency structure in which dependent claims inherit and refine the scope of earlier claims; however, existing patent en
arXiv:2605.10547v1 Announce Type: new Abstract: Electronic design automation (EDA) addresses placement, routing, timing analysis, and power-integrity verification for integrated circuits. Learning met
arXiv:2605.10118v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have demonstrated exceptional general reasoning capabilities. However, their performance in embodied navigation remains hi
arXiv:2605.09638v1 Announce Type: new Abstract: Ensuring the security of reinforcement learning (RL) models is critical, particularly when they are trained by third parties and deployed in real-world
arXiv:2605.08982v1 Announce Type: new Abstract: Monte Carlo Tree Search (MCTS) is a widely used approach for policy improvement through search with increasing popularity for real world applications. D
arXiv:2605.10816v1 Announce Type: cross Abstract: We study policy gradient methods for reinforcement learning in non-Markovian decision processes (NMDPs), where observations and rewards depend on the
arXiv:2605.08415v1 Announce Type: new Abstract: Since the advent of Large Language Models (LLMs), a significant area of research has focused on their intrinsic biases, particularly in political discou
arXiv:2605.09915v1 Announce Type: cross Abstract: The implicit policy of maintaining relatively stable acceptance rates at top AI conferences, despite exponentially growing submissions, introduces a c
arXiv:2509.12635v3 Announce Type: replace-cross Abstract: We prove under practical assumptions that Rotary Positional Embedding (RoPE) introduces an intrinsic distance-dependent bias in attention scor
arXiv:2605.09472v1 Announce Type: new Abstract: Positional encoding in transformers is commonly implemented through positional embeddings, attention masks, or bias terms, but formal connections betwee
arXiv:2605.09749v1 Announce Type: new Abstract: Discrete diffusion models generate structured sequences by progressively unmasking tokens, but enforcing global property constraints during generation r
Douglas Belkin / Wall Street Journal: Princeton faculty votes to require proctoring in all in-person exams starting this summer, reversing an 1893 policy amid concerns about AI-fueled cheating — The c
arXiv:2605.08651v1 Announce Type: cross Abstract: Video anomaly detection (VAD) systems often prioritize accuracy while overlooking privacy concerns, limiting their suitability for real-world deployme
arXiv:2605.08774v1 Announce Type: cross Abstract: Long-horizon robotic manipulation requires dense feedback that reflects how a task advances through its procedural stages, not merely whether the fina
arXiv:2605.10189v1 Announce Type: cross Abstract: Designing proteins with desired functions or properties represents a core goal in synthetic biology and drug discovery. Recent advances in protein lan
arXiv:2605.09893v1 Announce Type: cross Abstract: Large language models (LLMs) are often evaluated based on their stated values, yet these do not reliably translate into their actions, a discrepancy t
arXiv:2601.14234v3 Announce Type: replace-cross Abstract: We propose Q-learning with Adjoint Matching (QAM), a novel TD-based reinforcement learning (RL) algorithm that tackles a long-standing challen
arXiv:2605.08515v1 Announce Type: new Abstract: Unlike standard expected-return Reinforcement Learning (RL), Distributional RL (DRL) models the full return distribution, making it better-suited for un
arXiv:2605.10611v1 Announce Type: cross Abstract: This paper proposes a jailbreaking prompt detection method for large language models (LLMs) to defend against jailbreak attacks. Although recent LLMs
arXiv:2605.08776v1 Announce Type: new Abstract: Reasoning-centric large language models (LLMs) achieve strong performance by generating intermediate reasoning trajectories, but often incur excessive t
arXiv:2605.10805v1 Announce Type: new Abstract: Reasoning-capable large language models (LLMs) have recently been adopted as automated judges, but their benefits and costs in LLM-as-a-Judge settings r
arXiv:2605.09614v1 Announce Type: new Abstract: Long chain-of-thought (CoT) reasoning improves large vision--language models, but visual information often fades during generation, limiting long-horizo
arXiv:2605.08315v1 Announce Type: new Abstract: Existing LLM-based policy optimizers see only scalar rewards: that a policy scored 0.45, but not whether the agent got stuck in a loop, fell into a hole
arXiv:2605.08098v1 Announce Type: new Abstract: Kirigami is an increasingly useful fabrication method to produce shape-programmable metamaterial structures. However, inverse design remains difficult b