Knowledge catalogue
arXiv:2605.29152v1 Announce Type: new Abstract: Randomly initialized neural networks induce a prior over functions, but the predictor used in practice is produced only after training. We ask how much
arXiv:2605.29343v1 Announce Type: new Abstract: Speculative decoding accelerates large language model inference by pairing a target model with a lightweight draft model whose proposed tokens are verif
arXiv:2510.27607v3 Announce Type: replace Abstract: Augmenting vision-language-action models (VLAs) with world models is promising for robotic policy learning but faces challenges in jointly predictin
arXiv:2605.30350v1 Announce Type: cross Abstract: Robot manipulation critically depends on perception that preserves the action-relevant aspects of a scene. Yet most robot learning pipelines are built
arXiv:2602.08783v3 Announce Type: replace Abstract: Latent or continuous chain-of-thought methods replace explicit textual rationales with a number of internal latent steps, but these intermediate com
arXiv:2509.23730v2 Announce Type: replace Abstract: Large language models (LLMs) have recently advanced in reasoning when optimized with reinforcement learning (RL) under verifiable rewards. Existing
arXiv:2605.28865v1 Announce Type: cross Abstract: What does a world model learn from physical exploration, without any linguistic supervision? We argue the answer is organized by a single principle: t
arXiv:2605.29303v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) followed by reinforcement learning (RL) has become a standard post-training paradigm for large language models. This paradi
arXiv:2505.21876v2 Announce Type: replace-cross Abstract: Recent approaches for video generation with camera control often create anchor videos (i.e., rendered videos that approximate desired camera m
even if @scaling01 turns out to be wrong about some of these, I respect the specificity. a bit more specific: - OpenAI will flourish -> meaning they will stay at the frontier and their market cap cont
arXiv:2605.29161v1 Announce Type: cross Abstract: Generating realistic graph-structured data is challenging due to discrete connectivity, varying graph sizes, and class-specific structural patterns. R
arXiv:2605.29394v1 Announce Type: new Abstract: While large language models (LLMs) excel at static scientific reasoning, they struggle to model the temporal structure of dynamic physical processes. We
arXiv:2605.29847v1 Announce Type: new Abstract: Reinforcement Learning (RL) has significantly advanced Large Language Models (LLMs) in verifiable domains, but aligning models for open-ended generation
exactly this. @Michael14kBall @GaryMarcus @Vivek4real_ He's been publicly trashed by AI boosters this whole time, in dismissive terms. And the thing he's doing, with a number of others, is to try to c
arXiv:2605.30062v1 Announce Type: new Abstract: The development of generative artificial intelligence technologies has propelled the visual realism of synthetic images to an unprecedented level. Altho
arXiv:2605.29793v1 Announce Type: new Abstract: Given an untrimmed video and a sentence query, video moment retrieval using language (VMR) aims to locate a target query-relevant moment. Since the untr
arXiv:2605.29937v1 Announce Type: cross Abstract: Diffusion models are effective for waypoint prediction in visual navigation, but standard sampling and test time guidance can produce unreliable or in
arXiv:2605.29461v1 Announce Type: new Abstract: LLM-conditioned segmentation has recently advanced rapidly by coupling large language models with iterative mask generation frameworks. However, we iden
arXiv:2510.12152v2 Announce Type: replace-cross Abstract: We study the decoupled multi-armed bandit problem, where the learner separately selects one arm for exploration and one, possibly different, a
Reuters: Former Tesla data labelers say FSD relies on laborious mapping for hazards; crash data analysis shows Tesla exaggerates FSD's safety via flawed methodology — Tesla says its Full Self-Driving
arXiv:2605.28826v1 Announce Type: new Abstract: In modern LLMs, linguistic features function not as stylistic artifacts but as probes of probability mass, allocated under training alignment objectives
arXiv:2605.29565v1 Announce Type: new Abstract: Vision-based approaches have become the dominant paradigm for traversability estimation in unstructured outdoor environments, typically adapting vision
fully agree! Artificial intelligences do not undergo experiences, do not possess a body, do not feel joy or pain, do not mature through relationships, and do not know from within what love, work, frie
arXiv:2605.30083v1 Announce Type: new Abstract: Autoregressive (AR) video generation has emerged as a promising paradigm for long-horizon video synthesis, where each frame is generated conditioned on
arXiv:2605.28995v1 Announce Type: new Abstract: Recent approaches integrating vision-language models (VLMs) as prompt encoders for generative model conditioning typically rely on expensive end-to-end
arXiv:2605.29584v1 Announce Type: new Abstract: Reinforcement learning (RL) is a natural fit for agentic knowledge base question answering (KBQA), where a model must issue executable actions, observe
arXiv:2602.17200v2 Announce Type: replace Abstract: Despite high semantic alignment, modern text-to-image (T2I) generative models still struggle to synthesize diverse images from a given prompt. In th
arXiv:2605.30282v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have recently shown strong potential for robot learning by following language instructions. However, in practice, la
arXiv:2605.29398v1 Announce Type: cross Abstract: Reinforcement learning (RL) can be used to improve the policy (denoiser) of diffusion large language models (dLLMs), while being hindered by the intra
arXiv:2605.29980v1 Announce Type: cross Abstract: Multimodal alignment of histopathology encoders with transcriptomic and genomic data has been shown to significantly improve performance in downstream
arXiv:2605.29661v1 Announce Type: new Abstract: Monocular 3D shape recovery is fundamental to geometric understanding, yet achieving robust generalization across arbitrary viewpoints and unseen object
arXiv:2601.17670v2 Announce Type: replace-cross Abstract: Mathematical programming is widely employed across various sectors - such as logistics, energy, and workforce planning - to model and solve in
arXiv:2510.26270v2 Announce Type: replace Abstract: Multi-step LLM agents in interactive environments represent a crucial step toward long-horizon decision-making. To train such agents, group-based re
arXiv:2605.29307v1 Announce Type: cross Abstract: Large Language Model (LLM) search agents have shown strong promise for knowledge-intensive language tasks through multiple rounds of reasoning and inf
arXiv:2605.30307v1 Announce Type: new Abstract: We present GR3D, a spatial vision language model equipped with three complementary grounding capabilities--explicit 2D grounding, implicit 2D grounding,
arXiv:2509.21154v4 Announce Type: replace-cross Abstract: Process reward models (PRMs) allow for fine-grained credit assignment in reinforcement learning (RL), and seemingly contrast with outcome rewa
arXiv:2605.30214v1 Announce Type: new Abstract: Third-person singular pronouns have long been used to study stereotypical biases in language models and to test their abilities to reason about referenc
arXiv:2605.29198v1 Announce Type: new Abstract: Group-advantage-based reinforcement learning methods, such as GRPO and DAPO, have demonstrated strong performance across diverse domains, including math
arXiv:2605.29262v1 Announce Type: new Abstract: The Dynamic Flexible Job Shop Scheduling Problem (DFJSP) necessitates a trade-off between instant reaction to stochastic disturbances and global optimiz
arXiv:2605.29816v1 Announce Type: new Abstract: The work presents an approach for addressing the challenge of robustness in Large Language Models (LLMs) to alterations and potential errors caused by s
arXiv:2605.30232v1 Announce Type: cross Abstract: How does reinforcement learning shape a language model's internal representations? We present evidence that RL recruits a pre-existing representation
arXiv:2605.30201v1 Announce Type: cross Abstract: We investigate a narrow but common failure mode of GRPO-style reinforcement learning in the context of sparse verifiable rewards: early updates contai
i have strong reason to believe this is cope. we may find out soon… Im calling BS on this story. 1. That would be 100,000 employees spending 5k/mo each or 10,000 employees averaging 50k/mo each. No wa
arXiv:2605.29776v1 Announce Type: new Abstract: Vision-Language Models (VLMs) such as CLIP demonstrate strong zero-shot generalization, but their performance significantly degrades in cross-domain sce
arXiv:2605.30323v1 Announce Type: cross Abstract: Reinforcement Learning from Human Feedback (RLHF) typically relies on static reward models to align Large Language Models with human preferences. Howe
arXiv:2605.29822v1 Announce Type: cross Abstract: Large language models (LLMs) have become integral to modern software development, enabling automated code generation at scale. However, validating the
arXiv:2605.29405v1 Announce Type: new Abstract: Decision-making from offline datasets typically warm-starts a policy or score model from fixed offline data and then refines it with limited online inte
arXiv:2604.17176v2 Announce Type: replace-cross Abstract: Future spacecraft operations require autonomy that can interpret high-level mission intent while preserving safety. However, existing trajecto
Gary Marcus is requesting that someone complete a form or document and submit it to him or another person (possibly Gary Marcus himself based on the mention of @GaryMarcus). The post appears to be a r
It’s a good day when the Pope vouches for your recent comment in Nature. The Pope is making exactly our point. LLMs “may imitate or even simulate, but they do not understand.” This is the core epistem
It's a shame what happened to @kevinroose. He used to be a pretty damn good tech reporter. But recently he got one-shotted by spending too much time in/around the big AI Labs (research for the book he
arXiv:2410.15236v4 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have transformed artificial intelligence by advancing natural language understanding and generation, enabling app
arXiv:2605.29509v1 Announce Type: new Abstract: In recent years, training-free video generation has progressed remarkably. However, when handling complex textual instructions, existing methods still s
arXiv:2205.04297v2 Announce Type: replace-cross Abstract: This paper proposes a learning-based visual peg-in-hole that enables training with several shapes in simulation, and adapting to arbitrary uns
arXiv:2605.30042v1 Announce Type: new Abstract: Automating scientific computing workflows requires more than generating executable code: autonomous systems must also select appropriate computational s
Lee Kuan Yew abolished trial by jury in Singapore after determining that it was too easy for defence lawyers to appeal to racial and religious biases of juries in multicultural Singapore. He writes in
arXiv:2508.19282v4 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) has emerged as a promising paradigm for improving the timeliness of knowledge updates and the factual acc
arXiv:2605.29864v1 Announce Type: new Abstract: Multi-step robot manipulation requires acting under uncertainty about how the scene will evolve, making exploration and policy adaptation challenging. W
arXiv:2605.30273v1 Announce Type: cross Abstract: Large language models (LLMs) show promise in generating supportive responses for mental health queries, but improving their usefulness, empathy, and s
arXiv:2605.30265v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have achieved substantial progress across a wide range of understanding and reasoning tasks, driven by large-scale image