Knowledge catalogue
arXiv:2505.10457v3 Announce Type: replace-cross Abstract: Incremental learning is a machine learning paradigm where a model learns from a sequential stream of tasks. This setting poses a key challenge
arXiv:2604.00208v2 Announce Type: replace Abstract: Comparing internal representations is a central goal in neuroscience and machine learning, but standard linear alignment metrics (Representational S
arXiv:2606.24255v1 Announce Type: cross Abstract: Although text-to-motion generation has achieved strong progress in synthesizing realistic single-person motions from language, extending it to text-dr
arXiv:2503.00069v2 Announce Type: replace-cross Abstract: Recent progress in large language models (LLMs) has focused on producing responses that meet human expectations and align with shared values -
arXiv:2606.24049v1 Announce Type: new Abstract: In robot learning, scaling training datasets across diverse embodiments and environments has become a dominant paradigm for learning generalizable robot
arXiv:2606.24165v1 Announce Type: new Abstract: Reducing visual token redundancy is critical for accelerating Multimodal Large Language Models (MLLMs) without degrading cross-modal reasoning performan
arXiv:2606.17165v3 Announce Type: replace-cross Abstract: Organizations and researchers show increasing interest in using large language models (LLMs) in place of human participants in A/B tests, in t
arXiv:2606.24712v1 Announce Type: cross Abstract: Humans effortlessly locate and identify objects by touch alone, even without vision. In contrast, robotic systems rely heavily on vision and struggle
“The Al bubble is by far the biggest stock-market bubble that mankind has ever seen - both in scale and scope, in terms of the leverage that's in there and in terms of the sheer excessive exuberance t
The problem we face with AI today is not a technical problem, it is a political problem. Of who gets to decide. What level of risk the public is exposed to, what future we build towards or avert. It's
Gary Marcus argues that generative AI, while significant, represents only a narrow subset of the broader computing field and should not overshadow the diverse and impactful work occurring across other
arXiv:2606.24622v1 Announce Type: new Abstract: Training safe Reinforcement Learning (RL) systems is inherently challenging, with no guarantee of avoiding unwanted behaviors. The most effective defens
Today I present you a curated collection of @tszzl saying that Fukuyama is always right We Need an International Treaty to Ban Superintelligence https://open.substack.com/pub/persuasion1/p/time-for-a-
arXiv:2606.24021v1 Announce Type: new Abstract: In modern generative models, images are specified and controlled through text prompts. In practice, images are generated from sequences of tokens derive
arXiv:2605.13076v2 Announce Type: replace Abstract: The LLM-based generation of machine-readable outputs such as JSON has attracted significant attention for integration with external systems. However
arXiv:2606.24333v1 Announce Type: new Abstract: In-Image Machine Translation (IIMT) aims to translate scene text in an image and render the translated text back into the original regions while preserv
arXiv:2606.24501v1 Announce Type: new Abstract: This paper describes UOL@IDEM's closed-track submission to the BEA 2026 shared task on L1-aware vocabulary difficulty prediction. We model the task as r
This post likely references Gary Marcus's critical commentary on limitations or failures in generative AI systems, using 'Fizzle' as a metaphorical or literal descriptor for underperformance or unmet
arXiv:2606.24516v1 Announce Type: new Abstract: A growing family of training-free solvers -- FlowDPS, FLOWER, PnP-Flow and their diffusion ancestors (DPS, DAPS) -- repurpose a pretrained flow-matching
arXiv:2407.18957v5 Announce Type: replace-cross Abstract: Can AI Agents simulate real-world trading environments to investigate the impact of external factors on stock trading activities (e.g., macroe
arXiv:2606.24619v1 Announce Type: new Abstract: Competency Questions (CQs) are the central component of CQ-verification, an established process in which an ontology is evaluated against a set of natur
Wow even @MicahLasher thinks the OpenAI-Andreessen-Palantir money spent to oppose @AlexBores backfired -- NY-12 retrospective in the NYT from Teddy Schleifer. Hard to imagine this was the headline tha
arXiv:2601.16192v2 Announce Type: replace Abstract: Lifting perspective images and videos to 360{eg} panoramas enables immersive 3D world generation. Existing approaches often rely on explicit geometr
arXiv:2606.22072v1 Announce Type: new Abstract: Apparent emotion in natural images is often not visible from the face alone. The face may be small, hidden, or neutral, while posture and scene context
arXiv:2606.22652v1 Announce Type: new Abstract: We propose Markov Chain from Human Feedback (MCHF), an elementary approach for aligning generative models from pairwise human preferences. Unlike Reinfo
arXiv:2606.20031v2 Announce Type: replace Abstract: Dynamic environmental changes, confined workspaces, and stringent real-time constraints make pathfinding in Robotic Mobile Fulfillment Systems (RMFS
arXiv:2606.21509v1 Announce Type: new Abstract: End-to-end autonomous driving systems tightly couple perception and decision-making through latent representations. Consequently, updates to perception
arXiv:2606.22360v1 Announce Type: new Abstract: Successful conversations require speakers to align on the meaning of concepts, a challenging but crucial task for human-robot interaction. Understanding
arXiv:2606.23574v1 Announce Type: cross Abstract: Vision-language-action (VLA) models and world-action models (WAM) are the generative models now driving general-purpose robot control, turning raw cam
arXiv:2606.23662v1 Announce Type: cross Abstract: Bayesian experimental design (BED) has traditionally been based on maximising expected uncertainty reductions from prior to posterior. A major shortfa
arXiv:2602.02451v2 Announce Type: replace Abstract: Discovering causal relationships requires controlled experiments, but experimentalists face a sequential decision problem: each intervention reveals
Gary Marcus argues that data security is fundamentally fragile and that mass surveillance and data harvesting practices create persistent security vulnerabilities that cannot be eliminated. The post e
arXiv:2606.21013v1 Announce Type: cross Abstract: Forecasting future events is a critical challenge for large language model (LLM) agents, spanning domains from elections and monetary policy to financ
AI Capex pushback from GS: 'If frontier intelligence can increasingly be developed in the East at a fraction of the cost incurred in the West … then the largest capital allocators are also the ones mo
AI data centres are hungry for land, water & power. I’m calling on every major AI company to publicly disclose the full environmental impact of its systems – as a matter of transparency No more hidden
arXiv:2602.12691v3 Announce Type: replace Abstract: We study how to improve large foundation vision-language-action (VLA) systems through human-in-the-loop reinforcement learning (RL) in real-world en
Although I supported Musk in his suit against OpenAI, and admire what he did for electric cars, I am afraid my considered overall view is not very different from this: Candidly I have no idea why anyo
arXiv:2505.10022v4 Announce Type: replace Abstract: Learning natural, animal-like locomotion from demonstrations has become a core paradigm in legged robotics. While motion tracking can reproduce refe
arXiv:2606.20687v1 Announce Type: new Abstract: Multi-Camera Multi-Target (MCMT) tracking has emerged as a critical capability for applications ranging from autonomous driving to animal behavior monit
arXiv:2606.22480v1 Announce Type: new Abstract: Learning visuomotor policies for long-horizon manipulation remains a fundamental challenge. Recent skill-based imitation learning methods based on discr
arXiv:2606.21525v1 Announce Type: new Abstract: Model-free reinforcement learning algorithms such as Proximal Policy Optimization (PPO) treat the environment as a black box, estimating policy gradient
arXiv:2606.21498v1 Announce Type: cross Abstract: Autoregressive text-to-image (T2I) generation has recently advanced rapidly, yet aligning generated images with human preferences remains challenging.
arXiv:2606.20701v1 Announce Type: cross Abstract: Learned communication improves coordination in cooperative multi-agent reinforcement learning, but it also creates a trust problem: a trained policy m
arXiv:2606.21645v1 Announce Type: cross Abstract: Large language models (LLMs) can readily reproduce conventional expressions, yet their ability to model gradient frequency distributions remains under
arXiv:2606.20812v1 Announce Type: new Abstract: EEG foundation models can learn generalizable representations from large-scale EEG corpora to enable single-backbone transfer across diverse clinical an
arXiv:2606.22456v1 Announce Type: new Abstract: Maintaining accurate navigation during GNSS outages remains a significant challenge for autonomous systems relying on low-cost inertial sensors. While c
arXiv:2601.22100v3 Announce Type: replace Abstract: Optimizing Conditional Value-at-risk (CVaR) using policy gradient (a.k.a CVaR-PG) faces significant challenges of sample inefficiency. This ineffici
arXiv:2606.23199v1 Announce Type: new Abstract: Attributed graph clustering partitions nodes by jointly exploiting node attributes and graph topology. It remains challenging due to attribute heterogen
arXiv:2606.22389v1 Announce Type: new Abstract: Singular Learning Theory leverages the Local Learning Coefficient (LLC) to quantify the geometry of neural network loss landscapes. However, mean-energy
arXiv:2606.21981v1 Announce Type: cross Abstract: While Large Language Models (LLMs) can generate fluent Arabic text, their ability to reliably control readability levels remains unclear. We propose a
arXiv:2606.21809v1 Announce Type: new Abstract: The presence of confounding bias poses a key challenge in policy evaluation, as the target causal effects of actions are not identifiable (i.e., underde
arXiv:2505.01652v2 Announce Type: replace Abstract: Fair machine learning seeks to identify and mitigate biases in predictions against unfavorable populations characterized by demographic attributes,
arXiv:2606.23206v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities in multimodal reasoning. However, prevailing reinforcement learning (RL)
arXiv:2602.03389v2 Announce Type: replace Abstract: Offline goal-conditioned reinforcement learning remains challenging for long-horizon tasks. While hierarchical approaches mitigate this issue by dec
arXiv:2507.08262v2 Announce Type: replace-cross Abstract: The spatial information inherent in 3D point clouds is crucial for robotic manipulation. However, existing 3D pre-training methods face a fund
arXiv:2606.19380v2 Announce Type: replace-cross Abstract: Software engineering and deployment are increasingly delegated to AI coding agents. The scale of their adoption is surfacing rare, but highly
arXiv:2603.22169v2 Announce Type: replace Abstract: We propose a new Verbal Reinforcement Learning (VRL) framework for interpretable task-level planning in mobile robotic systems operating under execu
arXiv:2606.21885v1 Announce Type: new Abstract: Foundation models have achieved remarkable performance across medical question answering, imaging, and electronic health record (EHR) tasks, yet reliabl
arXiv:2606.22963v1 Announce Type: new Abstract: Concept segmentation models like Segment Anything Model 3 (SAM3) show strong generalization on natural images, yet their performance degrades in medical
arXiv:2602.03762v3 Announce Type: replace-cross Abstract: Visually-guided acoustic highlighting seeks to rebalance audio in alignment with the accompanying video, creating a coherent audio-visual expe