Knowledge catalogue
arXiv:2508.03343v2 Announce Type: replace Abstract: Text-Motion Retrieval (TMR) aims to retrieve 3D motion sequences semantically relevant to text descriptions. However, matching 3D motions with text
arXiv:2607.29613v1 Announce Type: cross Abstract: Reinforcement learning (RL) post-training of Vision-Language-Action (VLA) models has shown strong promise for robotic manipulation. Among RL methods,
arXiv:2607.29617v1 Announce Type: cross Abstract: Imitation learning (IL)---training an agent to replicate expert behavior from demonstrations---underpins applications from robotics to language model
arXiv:2607.28829v1 Announce Type: cross Abstract: Self-improving federated agent networks keep training after deployment by collecting new trajectories with the current policy and feeding them back in
Checkmate: you can’t take the harness (which is typically in large part symbolic) away from the neural model without giving up performance. HUGE victory for neurosymbolic AI, straight from @AnthropicA
exactly. math isn’t done. not at all. I don’t think being critical of the amazing work AI is doing in pure math is fair to @OpenAI until I can start to say why I feel it’s not yet at the level of our
LLMs can know a task is impossible and still optimize it anyway. Ask whether to walk or drive to a car wash 50 meters away, and some models focus on distance while missing that the car itself must rea
OpenAI guy lies about my intent. I would absolutely love to see progress in AI for science and medicine. I have said that here, in my books, on countless podcasts, in multiple NYT opeds, in the US Sen
This wins the prize for sleazy misrepresentation. @mattShumer took my 2023 argument for hybridizing LLMs with symbolic tools – which is *exactly* what everyone does nowadays – and made it sound like I
Yet another paper argues that LLMs aren’t close to doing real discovery. MIT and Harvard argue LLMs are nowhere near doing real scientific discovery. They published a paper called “Evaluating Large La
I am trying to learn concepts like On Policy Distillation (OPD), On Policy Self Distillation (OPSD) and how do they compare to RL algorithms like GRPO. There are a lot of papers on this, but because o
If Leopold had read this on June 26 and trimmed his bets accordingly, SALP would not have melted down. I laid everything out. https://open.substack.com/pub/garymarcus/p/the-month-generative-ai-lost-it
The “AGI-is-near” community keeps committing the same logical fallacy over and over; I have seen it at least half a dozen times today alone. Every time there’s an advance, I see the same error. Here’s
arXiv:2505.10300v2 Announce Type: replace-cross Abstract: Responsible AI (RAI) efforts increasingly emphasize the importance of addressing potential harms early in the AI development lifecycle through
arXiv:2607.26069v1 Announce Type: cross Abstract: As AI systems are rapidly integrated into critical economic, governmental, and national security functions, the gap between AI adoption and AI securit
Anthropic employee vouches for fiancee of Dario’s chief of staff who holds a lot of Anthropic stock… Where do the Anthropic employees get their media training, exactly? Prediction: SALP will be bigger
arXiv:2607.28553v1 Announce Type: new Abstract: Predicting the 3D structures of atomic systems is fundamental to advancing material science and drug discovery. While flow-matching models (, FlowDPO) h
arXiv:2607.26946v1 Announce Type: new Abstract: Recent advancements in Computer Go, driven by AlphaZero and MuZero, rely heavily on Monte Carlo Tree Search (MCTS) to correct the errors of the neural n
arXiv:2607.27851v1 Announce Type: new Abstract: Emotional dialogue research includes two influential strategy traditions. Empathetic dialogue prioritizes understanding a speaker's emotional experience
arXiv:2512.00807v2 Announce Type: replace Abstract: Vision-Language Models (VLMs) inherit significant social biases from their training data, notably in gender representation. Current fairness interve
arXiv:2607.26639v1 Announce Type: cross Abstract: A self-check defense asks the target model to assess a request before answering it; SAGE, the strongest published instance, reports an average 99% def
arXiv:2607.27366v1 Announce Type: new Abstract: While data synthesis for large language models (LLMs) is prevalent, it primarily targets domains with verifiable answers, overlooking open-ended humanit
arXiv:2607.27651v1 Announce Type: new Abstract: Adaptive laboratories choose measurements during experiments, yet most methods begin after adaptation is permitted. We introduce Opportunity-aware Polic
arXiv:2607.27905v1 Announce Type: new Abstract: Counterfactual explanations (CFEs) enhance the interpretability of black-box models by generating alternative instances with adjusted feature values tha
arXiv:2607.28026v1 Announce Type: new Abstract: Recent advances in post-training Large Language Models (LLMs) increasingly rely on Reinforcement Learning with Verifiable Rewards (RLVR) or On-Policy Se
arXiv:2607.28513v1 Announce Type: new Abstract: Creativity is often framed as the production of novelty, yet many cultural works emerge through transformation of earlier artifacts and not through isol
arXiv:2607.27761v1 Announce Type: cross Abstract: In recent years, multi-view clustering has attracted widespread research interest. However, due to limitations in data collection devices, data across
arXiv:2607.27882v1 Announce Type: new Abstract: As generative models continue to evolve, AI-generated image detectors must incrementally adapt to emerging generative domains while preserving knowledge
arXiv:2607.27784v1 Announce Type: new Abstract: Scalable collection of dexterous manipulation demonstrations remains a major bottleneck for robot learning. High-fidelity interfaces often require costl
arXiv:2607.27212v1 Announce Type: cross Abstract: Children with Autism Spectrum Disorder in Arabic-speaking countries face compounded barriers to effective speech and language therapy: a shortage of q
arXiv:2607.27614v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have led sign language translation (SLT), the task of converting sign-language videos into spoken-langua
arXiv:2607.27891v1 Announce Type: cross Abstract: Temporal graph learning is commonly organized around the evolution of node states or the encoding of interaction histories. We study an underexplored,
arXiv:2607.26588v1 Announce Type: new Abstract: The rapid development of large language models (LLMs) has renewed interest in agent-based modeling (ABM). However, current LLM-based ABM research faces
arXiv:2607.28243v1 Announce Type: new Abstract: Egocentric video offers rich manipulation experience for embodied AI, yet collecting diverse egocentric data across scenes, objects, motions, and embodi
arXiv:2607.27655v1 Announce Type: new Abstract: Reported accuracy in electroencephalography (EEG) emotion recognition depends on the complete evaluation procedure, not only the classifier. We separate
Everyone’s going on about how smart Leopold Aschennbrenner is (or was). But 1. He obviously didn’t know anything at all about risk management. (Or arrogantly chose to disregard whatever he might have
arXiv:2607.28596v1 Announce Type: new Abstract: In contact-rich manipulation, action multimodality and reactivity dominate different stages of a single episode. Before contact, multiple trajectories m
arXiv:2607.27959v1 Announce Type: new Abstract: Due to their strong generalizable multimodal processing and reasoning capabilities, Multimodal Large Language Models (MLLMs) have demonstrated significa
arXiv:2607.28022v1 Announce Type: new Abstract: Large language model training in open-ended domains lacks verifiable rewards, making task preferences difficult to formalize as effective supervision. C
arXiv:2607.27217v1 Announce Type: cross Abstract: Forest aboveground biomass (AGB) is a critical indicator of ecosystem productivity and terrestrial carbon storage, yet regional carbon monitoring rema
arXiv:2607.26656v1 Announce Type: cross Abstract: Real-world vulnerabilities often span multiple functions, yet most learning-based detectors classify each function in isolation: on a sample of real C
arXiv:2607.28076v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) is effective for training large language model agents. However, terminal rewards provide only co
arXiv:2607.26071v1 Announce Type: cross Abstract: In this work, we propose GuidedRAG, a novel extension to traditional Retrieval-Augmented Generation (RAG) that introduces a dedicated selection stage
arXiv:2607.27636v1 Announce Type: cross Abstract: Recent agentic AI systems may return a heterogeneous response containing notices, requests, handoffs, and actions. Conditions can change before extern
arXiv:2607.27652v1 Announce Type: new Abstract: Reinforcement learning (RL) search agents commonly model retrieval as free-form natural-language query generation and optimize multi-turn interactions u
arXiv:2607.27928v1 Announce Type: new Abstract: The performance of Large Language Models (LLMs) is fundamentally influenced by the distributional composition of multi-domain pre-training data. While m
arXiv:2607.27577v1 Announce Type: cross Abstract: Heterogeneous recommendation feeds present complex challenges that extend beyond those found in highly homogeneous environments (e.g., music-only or v
arXiv:2607.27379v1 Announce Type: new Abstract: High-quality, diverse data are vital for large language models (LLMs) but remain scarce and costly. Data synthesis is a viable alternative and succeeds
openPangu-2.0-Pro is an MoE model trained on Ascend. The model has 505B total parameters and 18B activated parameters. Its context length is 512k. The total pretraining data contains 34T tokens. Durin
arXiv:2607.27564v1 Announce Type: new Abstract: Multi-image medical VQA is not merely a prompt-length problem; it is a fundamental challenge of agentic decision-making. Medical vision-language agents
arXiv:2607.27909v1 Announce Type: cross Abstract: Objective evaluation of expressive MIDI piano performances typically relies on attribute statistics such as timing, velocity, and duration of individu
arXiv:2607.27261v1 Announce Type: new Abstract: Visuomotor imitation learning has demonstrated success for manipulation tasks. However, the trained policies remain brittle to visual `nuisances', with
arXiv:2607.27922v1 Announce Type: new Abstract: Robots navigating among pedestrians typically sense their surroundings with a 2D LiDAR mounted close to the ground. At that height, the sensor mostly se
Krea 2 has been my favorite base model for character work, but the moment you put two character LoRAs in the same generation they smear into one blended face. Attention bias, prompt engineering, and C
arXiv:2607.27620v1 Announce Type: new Abstract: Deep learning has shown strong potential in medical image analysis, but most existing methods rely on large-scale annotations and a closed-world assumpt
arXiv:2607.28565v1 Announce Type: new Abstract: Medical image fusion aims to integrate complementary information from diverse imaging modalities to support clinical diagnosis. Existing methods typical
arXiv:2607.26698v1 Announce Type: cross Abstract: Cover song generation (CSG) should preserve the melodic and linguistic content of a reference song while recreating the remaining musical components.
arXiv:2607.27581v1 Announce Type: new Abstract: Grounding human motion in language, and language in motion, is a central step toward physical AI systems that can understand, generate, and communicate
arXiv:2607.28182v1 Announce Type: new Abstract: E-commerce platforms must allocate fixed marketing budgets across multiple channels to maximize business utility. However, standard predict-then-optimiz
arXiv:2607.27924v1 Announce Type: cross Abstract: In the physical world we inhabit, space and time are fundamentally continuous. However, existing machine learning paradigms for world modeling are lar