Knowledge catalogue
arXiv:2605.16245v1 Announce Type: cross Abstract: Generative artificial intelligence (AI) is increasingly integrated into the online platforms where humans exchange opinions; large language models (LL
arXiv:2605.15220v1 Announce Type: cross Abstract: Data mixing decides how to combine different sources or types of data and is a consequential problem throughout language model training. In pretrainin
“Americans are now more comfortable living near a nuclear power plant than an AI data center” -@RachelBitecofer The AI oligarchs took a winning hand, and with a mixture cigarette-industry level greed
arXiv:2605.16153v1 Announce Type: new Abstract: This paper provides an algebraic exposition of the theory of dyadic morality (TDM), a psychological model of moral judgment grounded in a simple two-nod
arXiv:2512.08052v3 Announce Type: replace-cross Abstract: Embodied agents, such as robots and virtual characters, must continuously select actions to execute tasks effectively, solving complex sequent
arXiv:2605.15565v1 Announce Type: cross Abstract: Reinforcement learning (RL) is increasingly used to improve the reasoning, coding, and tool-use capabilities of large language models, but agentic RL
arXiv:2602.01295v3 Announce Type: replace Abstract: We investigate episodic Markov Decision Processes with heavy-tailed losses (HTMDPs). Existing approaches for HTMDPs are conservative in stochastic e
arXiv:2601.21357v2 Announce Type: replace Abstract: Bayesian Optimization (BO) is a principled framework for optimizing expensive black-box functions, with Expected Improvement (EI) among its most wid
arXiv:2605.15312v1 Announce Type: cross Abstract: Large-scale facial datasets like CelebA are widely used in computer vision, yet the cultural biases embedded in their labels remain underexplored. Fai
arXiv:2507.01679v3 Announce Type: replace-cross Abstract: Existing LLMs-post-training techniques are broadly categorized into supervised fine-tuning (SFT) and reinforcement fine-tuning (RFT). Each par
Can we all agree that Dario played the “Ooh! AI scary!” card one time too many? “Americans are now more comfortable living near a nuclear power plant than an AI data center” -@RachelBitecofer The AI o
arXiv:2605.15354v1 Announce Type: new Abstract: Despite the success of foundation models in language and vision, molecular graph generation still lacks a unified framework for heterogeneous design tas
arXiv:2605.16113v1 Announce Type: cross Abstract: Large language models (LLMs) have achieved unprecedented success due to their exceptional generative capabilities. However, because they depend on kno
arXiv:2605.15942v1 Announce Type: cross Abstract: Open-vocabulary segmentation models often struggle to generalize to unseen combinations of object categories and attributes, because fine-grained desc
arXiv:2507.00275v2 Announce Type: replace-cross Abstract: Double Q-learning is a classical control algorithm that mitigates the maximization bias of Q-learning. To do so, it explicitly trains two inde
arXiv:2605.15532v1 Announce Type: cross Abstract: Distillation enables compact Vision-Language Models (VLMs) to obtain strong reasoning capabilities, yet the prompts driving this process are typically
arXiv:2605.16255v1 Announce Type: cross Abstract: Demand for AI accelerators is rapidly increasing rack power density, with projections approaching 1MW per deployment by 2027. This poses a major chall
arXiv:2503.00794v2 Announce Type: replace Abstract: Accurate gait event detection is crucial for gait analysis, rehabilitation, and assistive technology, particularly in exoskeleton control, where pre
arXiv:2605.15460v1 Announce Type: cross Abstract: Cross-modal hashing enables efficient retrieval by encoding images and text into compact binary codes. State-of-the-art methods rely on semantic simil
arXiv:2605.15352v1 Announce Type: new Abstract: Opening heavy, self closing doors, especially those that require pulling remains a long standing challenge in robotics. Humans naturally employ both arm
arXiv:2605.15519v1 Announce Type: cross Abstract: Visual active search (VAS) has been introduced as a modeling framework that leverages visual cues to direct aerial (e.g., UAV-based) exploration and p
arXiv:2605.15368v1 Announce Type: new Abstract: Group-convolutional neural networks (GCNNs) are among the most important methods for introducing symmetry as an inductive bias in deep learning: In each
arXiv:2605.15855v1 Announce Type: new Abstract: Despite strong image-generation performance, diffusion models' reconstruction objectives limit alignment with human preferences. RL enables such alignme
arXiv:2511.19399v3 Announce Type: replace-cross Abstract: Deep research agents perform multi-step research to produce long-form, well-attributed answers. However, most open deep research agents are tr
arXiv:2512.09673v3 Announce Type: replace-cross Abstract: Equivariant neural networks encode the intrinsic symmetry of data as an inductive bias, which has achieved impressive performance in wide doma
arXiv:2605.15422v1 Announce Type: new Abstract: Modern RL post-training methods such as GRPO and DAPO train on N response sequences of R tokens sampled from a shared prompt of P tokens, but standard F
arXiv:2508.17034v2 Announce Type: cross Abstract: Noisy, partially overlapping data and the need for real-time processing pose major challenges for rigid registration. Considering that feature-based m
arXiv:2605.15935v1 Announce Type: new Abstract: Plasma shape control in tokamaks requires a real-time controller that tracks dynamically changing shape targets while tolerating diagnostic failures. Cl
arXiv:2509.23352v3 Announce Type: replace-cross Abstract: The integration of Reinforcement Learning (RL) into flow matching models for text-to-image (T2I) generation has driven substantial advances in
arXiv:2602.01568v2 Announce Type: replace-cross Abstract: Multi-robot coordination often exhibits hierarchical structure, with some robots' decisions depending on the planned behaviors of others. Whil
arXiv:2605.15477v1 Announce Type: new Abstract: Egocentric world models present a promising direction for enabling agents to predict and plan, but their performance is constrained by the limited avail
arXiv:2605.15684v1 Announce Type: new Abstract: The Diffusion Transformer (DiT) architecture is the state-of-the-art paradigm for high-fidelity image generation, underpinning models like Stable Diffus
arXiv:2605.15803v1 Announce Type: new Abstract: Recent advancements have established Reinforcement Learning (RL) as a pivotal paradigm for aligning generative models with human intent. However, group-
arXiv:2605.15586v1 Announce Type: cross Abstract: Complementary-label learning (CLL) is a weakly supervised paradigm where instances are labeled with classes they do not belong to. Despite a decade of
arXiv:2605.15711v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities across various tasks, yet they remain vulnerable to backdoor attacks. Exi
arXiv:2605.15380v1 Announce Type: new Abstract: Recent advances in generative AI have shown their potential to be leveraged for legal education. Yet, work on the development and deployment of such sys
arXiv:2605.16041v1 Announce Type: cross Abstract: Machine learning systems increasingly make life-changing decisions about individuals, such as loan approvals, hiring, and cheating detection, raising
arXiv:2605.15417v1 Announce Type: cross Abstract: In GFlowNets and variational inference, it has been shown that the mean square error between target and model log probabilities is an effective, low v
arXiv:2604.05966v2 Announce Type: replace Abstract: Financial reporting systems increasingly leverage Large Language Models (LLMs) to extract and summarize corporate disclosures. However, most existin
arXiv:2605.15492v1 Announce Type: cross Abstract: Generative models such as diffusion and flow matching have become dominant paradigms for visuomotor policy learning, yet their reliance on iterative d
arXiv:2604.04539v2 Announce Type: replace Abstract: Reinforcement learning (RL) is a core approach for robot control when expert demonstrations are unavailable. On-policy methods such as Proximal Poli
arXiv:2410.02832v2 Announce Type: replace-cross Abstract: This paper proposes a simple yet effective jailbreak attack named FlipAttack against black-box LLMs. First, from the autoregressive nature, we
arXiv:2602.23566v2 Announce Type: replace-cross Abstract: We study generative modeling of graphs with recurring subgraph motifs. We propose Flowette, a continuous flow matching framework that employs
arXiv:2605.15944v1 Announce Type: cross Abstract: Visuomotor policies aim to learn complex manipulation tasks from expert demonstrations. However, generating smooth and coherent trajectories remains c
I cannot provide an accurate summary without access to the actual content of this post. The title fragment suggests Rachel Bitecofer provided factual information shared by Gary Marcus on X (Twitter),
arXiv:2605.15241v1 Announce Type: cross Abstract: Single-unit crown restoration is among the most common procedures in clinical dentistry, with CAD/CAM workflows now designing crowns directly from int
arXiv:2605.15334v1 Announce Type: cross Abstract: The automatic synthesis of a program from any form of specification is regarded as a holy grail of computer science. Fueled by LLMs, NL2Code has achie
arXiv:2506.22440v2 Announce Type: replace-cross Abstract: This paper introduces the Generality-Accuracy-Simplicity (GAS) framework to analyze how large language models (LLMs) are reshaping organizatio
arXiv:2602.20630v4 Announce Type: replace Abstract: Keypoint-based matching is a fundamental component of modern 3D vision systems, such as Structure-from-Motion (SfM) and SLAM. Most existing learning
arXiv:2605.15328v1 Announce Type: new Abstract: Fully Connected Neural Networks (FCNNs) are often regarded as simple and intuitive architectures, yet they serve as the foundation for more complex mode
arXiv:2605.15836v1 Announce Type: cross Abstract: Learning visuomotor policies from scarce expert demonstrations remains a core challenge in robotic manipulation. A primary hurdle lies in distilling h
arXiv:2605.15575v1 Announce Type: new Abstract: Relational graph learning models relational databases as graphs and has demonstrated superior performance on a wide range of relational predictive tasks
arXiv:2508.17218v3 Announce Type: replace-cross Abstract: Reliable path planning in stochastic transportation networks requires decisions that account for uncertain and correlated travel times on irre
arXiv:2605.15491v1 Announce Type: cross Abstract: Layer pruning removes entire Transformer decoder blocks from large language models, but introduces a mismatch between the hidden state received by the
arXiv:2605.15723v1 Announce Type: cross Abstract: Multimodal alignment is commonly learned from isolated image-text pairs via CLIP-style dual encoders, leaving the relational context among entities la
arXiv:2605.15336v1 Announce Type: cross Abstract: In this report, we present HoloMotion-1, a humanoid motion foundation model for zero-shot whole-body motion tracking. A key innovation of HoloMotion-1
arXiv:2603.03243v2 Announce Type: replace Abstract: We present Whole-Body Mobile Manipulation Interface (HoMMI), a data collection and policy learning framework that learns whole-body mobile manipulat
arXiv:2605.15741v1 Announce Type: new Abstract: Pixel-space diffusion models bypass the reconstruction bottleneck of Variational Autoencoders (VAEs) but face a fundamental 'granularity dilemma': captu
arXiv:2605.15960v1 Announce Type: new Abstract: We propose a novel definition of model exploitation in reinforcement learning. Informally, a world model is exploitable if it implies that one policy sh
This newsletter explores three AI topics: potential weaponization risks of AI systems (framed as 'AI stuxnet'), issues with the Muon optimizer in machine learning, and progress or approaches toward po