Knowledge catalogue
arXiv:2606.26522v1 Announce Type: new Abstract: While corporate narrative disclosures provide crucial information to capital markets, comprehensively evaluating their qualitative changes over time rem
arXiv:2606.26396v1 Announce Type: new Abstract: Pre-trained transformers have demonstrated remarkable generalization abilities, at times extending beyond the scope of their training data. Yet, real-wo
arXiv:2606.27180v1 Announce Type: cross Abstract: Sparse rewards are inherently challenging for reinforcement learning agents as they lack intermediate feedback to guide exploration and to correctly a
Gary Marcus argues that poor performance in military applications correlates with or reflects fundamental weaknesses in AI capabilities and development. The post likely critiques limitations in curren
arXiv:2606.26406v1 Announce Type: cross Abstract: We propose a complete architectural blueprint for safe artificial general intelligence based on a closed reentry loop (D I cycle). In contrast to feed
arXiv:2606.26603v1 Announce Type: new Abstract: Handheld data collection systems, such as the Universal Manipulation Interface (UMI), enable scalable data collection across diverse environments but on
arXiv:2606.27348v1 Announce Type: new Abstract: Autonomous drone racing is a fundamentally challenging regime for autonomous aerial robots, requiring time-optimal control while operating under persist
arXiv:2606.26763v1 Announce Type: new Abstract: Implicit neural representation (INR) has emerged as a powerful prior for multi-dimensional data (e.g., multispectral images and videos). However, most I
arXiv:2606.26933v1 Announce Type: cross Abstract: AI-assisted vulnerability discovery has proven effective for bug classes like memory safety, where instrumentation confirms memory violations and effi
arXiv:2606.27353v1 Announce Type: new Abstract: Robots deployed in the real world rarely operate under a single fixed dynamics model: wind changes, payloads vary, batteries drain, contacts shift, and
Gary Marcus posted a correction regarding a New York Times report about a company contemplating delays to their IPO plans. The post appears to address inaccuracies or clarifications needed in the orig
arXiv:2606.26423v1 Announce Type: cross Abstract: Long-horizon, contact-rich complex manipulation tasks, such as seating a GPU into a PCIe slot, demand both millimeter high precision and out-of-the-bo
arXiv:2606.27114v1 Announce Type: new Abstract: Uplift modeling, crucial for estimating individual treatment effects (ITE), faces dual challenges: flexibly leveraging inter-group similarity to enhance
arXiv:2510.20769v2 Announce Type: replace-cross Abstract: Accurate medium-range precipitation forecasting is essential for hydrometeorological risk management but remains challenging for both numerica
arXiv:2606.27095v1 Announce Type: cross Abstract: Cold-start exemplar-free class-incremental learning requires learning a growing set of classes without replay, external pretraining, or a large initia
arXiv:2409.01447v3 Announce Type: replace Abstract: We present a finite-sample analysis of decentralized learning in two-player zero-sum matrix games and stochastic games, with a focus on best-respons
arXiv:2606.26743v1 Announce Type: new Abstract: Point clouds are an important carrier of three-dimensional spatial information, and their quality directly affects the performance of downstream percept
arXiv:2606.27291v1 Announce Type: new Abstract: Job-search platforms rely on low-bandwidth query interfaces that often fail to capture the high-dimensional complexity of candidate profiles. We present
arXiv:2606.26397v1 Announce Type: cross Abstract: Real-world decision-making often requires balancing multiple conflicting objectives, a challenge that standard Reinforcement Learning (RL) frequently
arXiv:2606.26918v1 Announce Type: new Abstract: Large language models can serve as capable long-horizon agents, but their out-of-distribution (OOD) generalization remains weak. We identify a key sourc
arXiv:2606.26122v1 Announce Type: new Abstract: Recent methods train search agents via reinforcement learning from (question, answer, evidence) tuples without requiring expert trajectories. The tuples
arXiv:2606.27371v1 Announce Type: new Abstract: State-of-the-art flow models generate stunning images from text or image prompts. However, they suffer from diversity collapse when generating multiple
arXiv:2606.26114v1 Announce Type: cross Abstract: We examine the structural transformation of creative industries under generative artificial intelligence, drawing on 374 primary sources spanning poli
arXiv:2606.27268v1 Announce Type: cross Abstract: Recently, a few works have made early attempts to study test-time scaling for embodied tasks. However, two major challenges remain unsolved: (1) reaso
arXiv:2606.27246v1 Announce Type: new Abstract: We study a solvable high-dimensional model of generative adversarial network (GAN) training in which a linear generator learns a low-dimensional subspac
arXiv:2606.26327v1 Announce Type: cross Abstract: In actor-critic reinforcement learning, network architectures are typically manually designed. Automating this design is challenging because each cand
Fantastic interview: Ed Elson is talking with Gary Marcus about AI tech, overrelience on LLMs, the business of AI, etc. I totally enjoyed this: https://youtu.be/_pSivPlRx5o?si=dzrJKpUGTHE0Y76I @edels0
arXiv:2606.26463v1 Announce Type: new Abstract: Deliberating takes time. In real-time settings, that time is not free. Standard reinforcement learning (RL) sidesteps this as the environment waits inde
arXiv:2606.27199v1 Announce Type: new Abstract: Successful forecasting involves identifying patterns between historical and future states of the world which generalize to future observations. We apply
arXiv:2606.26535v1 Announce Type: cross Abstract: Current VLM evaluations often conflate language priors with genuine spatial reasoning. To address this, we introduce CRISP, a novel structural-diagnos
Traditional alerting systems often force a compromise: you can either alert immediately on simple, noisy log events, or monitor rigid, pre-configured metrics that fail when faced with data with many u
from tokenmaxxing to this in less than three months. anyone who doesn’t see this as affecting Anthropic and OpenAI is not paying attention. UBS says 60% of companies now watching AI budgets are moving
“Gary Marcus … says that investments into scaling AI is the “greatest capital misallocation in history” which leaves everyone “on the hook”. However, he also says that it is still early days for the A
Gary Marcus discusses fundamental challenges and limitations in current AI systems during an interview, likely covering topics such as the gap between narrow and general intelligence, reasoning limita
arXiv:2606.26899v1 Announce Type: new Abstract: Embedding-based retrieval ranks items by their similarity to a query in a shared vector space and usually aims to return the highest-scoring items. In m
arXiv:2606.26917v1 Announce Type: cross Abstract: Online reinforcement learning is widely used to align large language models (LLMs) with reward signals, yet training can be unstable under noisy or mi
arXiv:2606.26125v1 Announce Type: cross Abstract: Emerging 6G and edge-intelligent networks require effective and balanced routing algorithms among varied and spatially distributed devices. Existing f
arXiv:2606.26298v1 Announce Type: new Abstract: Autonomous AI agents may begin to perform consequential, irreversible actions such as clinical prescribing and production software deployment. This pape
arXiv:2606.27202v1 Announce Type: new Abstract: Graph neural networks have moved from a niche representation-learning technique to the default model class wherever data carry relational structure. The
arXiv:2606.12816v3 Announce Type: replace-cross Abstract: Quantum circuit routing is a key step in compiling programs for noisy intermediate-scale quantum processors. Routes that appear efficient by s
arXiv:2606.26643v1 Announce Type: new Abstract: This paper focuses on the hardware specifications required for a table tennis robot to beat professional players. After analyzing the motions of elite p
arXiv:2506.07031v5 Announce Type: replace-cross Abstract: Emerging Large Reasoning Models (LRMs) consistently excel in mathematical and reasoning tasks, showcasing remarkable capabilities. However, th
arXiv:2606.26100v1 Announce Type: new Abstract: Media bias detection is a critical task for ensuring fair and balanced information dissemination, yet existing sentence-level approaches classify each s
arXiv:2606.26316v1 Announce Type: new Abstract: We study first-order methods for smooth objectives satisfying the Polyak-L{}ojasiewicz (PL) condition when gradient samples are generated by an exogenou
Dean W. Ball / Hyperdimensional: How US federal AI policy has gone from implausibly libertarian to increasingly draconian and opaque, and how to fix it, including using independent auditors — 35 thoug
arXiv:2510.26518v2 Announce Type: replace Abstract: Human feedback is critical for aligning AI systems to human values. As AI capabilities improve and AI is used to tackle more challenging tasks, veri
arXiv:2606.26855v1 Announce Type: new Abstract: Imitating human demonstrations has emerged as a dominant paradigm for learning humanoid loco-manipulation policies. However, scaling these approaches re
arXiv:2606.27239v1 Announce Type: new Abstract: High-quality demonstration data are essential for humanoid robot skill learning, especially for whole-body behaviors that require coordinated perception
arXiv:2606.26502v1 Announce Type: new Abstract: Large reasoning models (LRMs) take longer on harder problems, just as humans do. This surface similarity hides an opposite pattern within items. When an
Connor Leahy argues that accumulating personal capital provides no protection against disempowerment by superintelligent AI systems, suggesting that wealth alone cannot guarantee security or agency in
arXiv:2606.26575v1 Announce Type: cross Abstract: Complex multi-agent control tasks remain challenging for traditional rule-based and model-based approaches, motivating the adoption of learning-based
arXiv:2512.23816v2 Announce Type: replace-cross Abstract: In this paper, we study the private and robust alignment of language models from a theoretical perspective by establishing upper bounds on the
arXiv:2606.27025v1 Announce Type: new Abstract: Building general-purpose role-playing agents that faithfully portray any character from a natural-language profile remains challenging. The dominant par
arXiv:2606.26801v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have shown strong potential for generalizable robotic manipulation. During fine-tuning, however, action supervisio
In a matter of weeks, U.S. federal AI policy has gone from implausibly libertarian to increasingly draconian and opaque. Today, over 35 distinct observations, I analyze how we got here and offer the m
arXiv:2606.26981v1 Announce Type: cross Abstract: Synthesizing human motion from textual descriptions is essential for immersive digital applications, yet existing methods face a persistent trade-off
Gary Marcus discusses arguments surrounding trillion-dollar implications, likely related to AI development, regulation, or economic impacts given his expertise in artificial intelligence and cognitive
arXiv:2606.26588v1 Announce Type: new Abstract: A central challenge in deploying learned robot policies is inference-time behavior steering: redirecting a policy at test time to satisfy user preferenc
June has been a dark month for the US generative AI industry, between hamfisted US policy and the transition to cheaper Chinese AI models. And then there is the delay of the OpenAI IPO. Is that the co
arXiv:2606.27023v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) applied to Medical Visual Question Answering (VQA) tend to produce overconfident outputs regardless of actual