Knowledge catalogue
arXiv:2610.11724v1 Announce Type: new Abstract: Multimodal meme understanding is increasingly used to analyze socially sensitive content, yet existing models often exhibit biased behavior when interpr
arXiv:2610.11060v1 Announce Type: cross Abstract: World-action models have recently improved autonomous driving by jointly learning future scene prediction and trajectory generation. Most existing app
arXiv:2603.08706v2 Announce Type: replace Abstract: Imitation learning (IL) teaches language-model agents to reproduce expert actions but not to distinguish them from plausible mistakes. Self-reflecti
Automated evals can score every agent session, but they do not automatically reflect what your team considers a good outcome. That takes human judgment. The post Alignment is a human-AI workflow: how
arXiv:2610.11213v1 Announce Type: new Abstract: Long-term Time Series Forecasting (LTSF) tasks, which leverage the current data sequence as input to predict the future sequence, have become increasing
arXiv:2610.12083v1 Announce Type: cross Abstract: LLM-as-a-Judge is the standard paradigm for NLP evaluation, yet its systemic reliability remains poorly understood despite being widely treated as a d
Emily Forlini / Fortune: Anthropic is setting up a “presidential engagement” program for the 2028 US elections that will offer AI policy education to candidates in both parties — Anthropic is setting
arXiv:2610.12386v1 Announce Type: cross Abstract: The prevailing approach to improving robot foundation models (RFMs) relies on larger models, more robot demonstrations, and costly training at scale.
Assorted things I've been mulling over regarding agents in the economy: • Companies are in some sense the original superintelligence. It's often the case that they can use their amortized cognitive su
arXiv:2610.11792v1 Announce Type: cross Abstract: We present AuraLuxMuse, a novel system for automated aesthetic stage lighting design that integrates expert knowledge, representation learning, and pr
arXiv:2610.11128v1 Announce Type: new Abstract: A verified reference solution provides a correct trajectory for training a reasoning model. Alternatively, a prefix of the reference can guide the model
arXiv:2607.10169v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has become a dominant paradigm for enhancing LLMs' reasoning capabilities. However, RL algorithms with PPO-Clip ar
arXiv:2610.11461v1 Announce Type: cross Abstract: Natural-language style descriptions provide an interpretable interface between large language models (LLMs) and controllable text-to-speech (TTS). How
arXiv:2510.15866v2 Announce Type: replace Abstract: The clinical adoption of biomedical vision-language models is hindered by prompt optimization techniques that produce either uninterpretable latent
arXiv:2507.21037v3 Announce Type: replace Abstract: Cross-subject motor-imagery electroencephalography (MI-EEG) decoding remains challenging because substantial inter-subject variability can cause bot
arXiv:2610.10742v1 Announce Type: cross Abstract: AI systems increasingly rely on Large Language Models (LLMs) as core reasoning engines, making them targets for prompt injection and jailbreaks. Guard
arXiv:2610.12016v1 Announce Type: new Abstract: World models for control must capture which aspects of the environment respond to the agent's actions and which are relevant to reward. Generative world
arXiv:2610.12362v1 Announce Type: new Abstract: We consider policy optimization for online episodic tabular Markov decision processes (MDPs) with adversarial losses and bandit feedback. Policy optimiz
arXiv:2610.12156v1 Announce Type: new Abstract: To stream long videos while maintaining visual quality and temporal consistency, Self Forcing mitigates exposure bias through self-rollout training on s
arXiv:2610.11663v1 Announce Type: new Abstract: Deep reinforcement learning agents reach strong performance in real-time strategy games but can be brittle against opponents outside their training dist
arXiv:2610.11096v1 Announce Type: cross Abstract: Visual tracking across the air-water interface is challenged by splashes, bubbles, refraction, reflections, and abrupt appearance changes that can tem
arXiv:2610.12107v1 Announce Type: new Abstract: Generalized referring expression segmentation (GRES) requires dynamically balancing high-level semantics for identifying a variable number of language-s
arXiv:2610.10641v1 Announce Type: cross Abstract: Large language models (LLMs) offer promising potential for next-visit diagnosis prediction, owing to their ability to integrate longitudinal clinical
arXiv:2610.11085v1 Announce Type: new Abstract: Offline multi-task reinforcement learning (Offline MTRL) heavily depends on the quality and distribution of pre-collected data. However, existing method
arXiv:2610.11505v1 Announce Type: new Abstract: Humanoid robots possess the structural capability to traverse complex terrains. However, achieving stable t raversal without relying on perceived inform
arXiv:2610.11748v1 Announce Type: cross Abstract: U-Net inference for brain-tumor segmentation requires billions of multiply-accumulate operations, motivating hardware that can reduce computation dyna
arXiv:2610.12470v1 Announce Type: cross Abstract: While learning dexterous manipulation from a single human video offers a promising alternative to costly robot demonstrations, many recent methods pre
arXiv:2610.12094v1 Announce Type: cross Abstract: Particle filters are a standard tool for nonlinear state estimation, but their resampling step is discrete, preventing gradient-based learning in vari
arXiv:2610.12355v1 Announce Type: cross Abstract: Spatial reasoning remains a persistent weakness of vision-language models (VLMs), because RGB inputs do not directly provide geometric evidence. Exist
arXiv:2610.11510v1 Announce Type: new Abstract: Large language models (LLMs) often default to Modern Standard Arabic (MSA) when generating Arabic, even when prompted with dialectal Arabic. A natural e
arXiv:2610.11938v1 Announce Type: new Abstract: Adversarial attacks on vision-language models optimize an image toward a text target, then cite the attacked model's similarity score as evidence of suc
arXiv:2610.12468v1 Announce Type: cross Abstract: We present DreamTrue, a multi-view, cross-embodiment robot world model for action-faithful and physically plausible video prediction. Training such a
arXiv:2610.12095v1 Announce Type: new Abstract: Few-shot learning aims to recognize novel categories from limited labeled examples. Recent studies incorporate textual semantics to compensate for limit
arXiv:2610.11431v1 Announce Type: new Abstract: Motion estimation in echocardiography is essential for quantitative assessment of cardiac function and myocardial mechanics, but remains challenging due
arXiv:2610.12369v1 Announce Type: cross Abstract: Most robot policies keep a model in the control loop: a VLA maps observations to actions, and an Agent Harness, such as Agent-as-Policy or Harness VLA
arXiv:2610.11384v1 Announce Type: new Abstract: Reinforcement learning is commonly used to train language agents in interactive environments, but cannot be directly applied when rewards are unavailabl
arXiv:2603.17524v2 Announce Type: replace-cross Abstract: We study fine-grained execution-constraint following in vision-language-action (VLA) models. Given an invariant task goal, the policy must fol
arXiv:2610.11815v1 Announce Type: new Abstract: Tracking a novel object's 6D pose over long horizons currently requires either expensive onboarding or a reconstruction maintained throughout the sequen
arXiv:2610.11119v1 Announce Type: new Abstract: Vision-based reinforcement learning for robotic manipulation is sample-inefficient because RGB-D observations are high-dimensional and noisy. Privileged
arXiv:2610.11309v1 Announce Type: cross Abstract: Different optimizers can fit the same training data while selecting classifiers with substantially different geometries, but whether this difference p
arXiv:2610.11722v1 Announce Type: new Abstract: Physics-based human-object interaction has achieved robust single-agent manipulation skills, yet extending them to multi-agent cooperative tasks remains
arXiv:2610.10897v1 Announce Type: new Abstract: Physics-Informed Neural Networks (PINNs) are a widely used data-free method for solving Partial Differential Equations (PDEs) using machine learning. Wi
arXiv:2610.12440v1 Announce Type: new Abstract: Human demonstrations are a scalable data source for learning dexterous manipulation, but the embodiment gap prevents human motion from being executed di
arXiv:2610.12388v1 Announce Type: new Abstract: Reconstructing complete 3D object assets from monocular or sparse multi-view observations remains challenging. Generative 3D foundation models can compl
arXiv:2610.12391v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) often struggle to identify and use geometric relations in diagrams. Recent methods address this challenge by co
arXiv:2610.11854v1 Announce Type: cross Abstract: Reinforcement learning (RL) methods such as GRPO substantially improve large language model reasoning but often suffer from policy entropy collapse: t
arXiv:2610.11534v1 Announce Type: new Abstract: DNNs exhibit robustness and generalisation issues not seen in humans. They are also far less data-efficient learners, requiring considerably more traini
arXiv:2610.11175v1 Announce Type: cross Abstract: Modern data-driven decision-making methods, such as imitation learning (IL) and reinforcement learning (RL), have achieved great success in solving ma
arXiv:2610.10934v1 Announce Type: cross Abstract: Actuator degradation turns quadruped locomotion into a coordination problem requiring joints to compensate for lost actuation. Prior work suggests tha
arXiv:2610.11005v1 Announce Type: new Abstract: Safety-aligned language models often refuse a harmful request stated directly but answer the same request inside a role-play or narrative wrapper. We me
arXiv:2610.11281v1 Announce Type: cross Abstract: Large language models (LLMs) are commonly post-trained against LLM judges and other cheap surrogates because the true reward, such as human preference
arXiv:2610.12026v1 Announce Type: cross Abstract: Humanoid robots are a promising platform for general-purpose manipulation. Recent Vision-Language-Action (VLA) policies learn actions directly from mu
i wrote approximately 2000 tweets and articles (like Deep Learning is Hitting A Wall) about the importance of supplementing deep learning/ LLMs with neurosymbolic AI over a span of 25 years and the te
I’m super excited this paper is finally out! It’s an epic 210 page analysis of whether a durable pause on frontier AI training is feasible. I think this will be the best plan by most people’s lights (
arXiv:2509.09311v2 Announce Type: replace Abstract: Vision-language models (VLMs) have enabled strong zero-shot classification through image-text alignment. Yet, their purely visual inference capabili
arXiv:2603.25015v2 Announce Type: replace-cross Abstract: System prompt instructions that cooperate in English compete in Spanish, with the same semantic content, but opposite interaction topology. We
arXiv:2610.11320v1 Announce Type: new Abstract: Text-to-image models appear to reproduce the habits of the photographs they learned from. Analog clocks are an extreme case: in advertising, watches alm
arXiv:2610.10615v1 Announce Type: cross Abstract: Choosing which information to observe is central to prediction under limited observation budgets. We study JevForest, a feature acquisition policy tha
arXiv:2610.11662v1 Announce Type: new Abstract: Autonomous driving capabilities depend strongly on the distribution of scenarios encountered during training. Existing methods commonly construct or dyn
arXiv:2606.18810v2 Announce Type: replace-cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has driven substantial progress in training LLMs for reasoning tasks, but representative