Knowledge catalogue
arXiv:2605.20924v1 Announce Type: new Abstract: Designing effective task-level prompts is crucial for improving the performance of Large Language Models (LLMs). While prior work on instruction inducti
arXiv:2605.21466v1 Announce Type: new Abstract: Although existing video editing methods are generally feasible, they often require many costly iterations and still struggle to deliver high-quality yet
arXiv:2605.20919v1 Announce Type: new Abstract: Sutra is a typed, purely functional programming language whose compiled forward pass is a PyTorch neural network. The compiler beta-reduces the whole pr
arXiv:2605.20347v1 Announce Type: new Abstract: Labeling a training set is often expensive and susceptible to errors, making the design of robust loss functions for label noise an important problem. T
arXiv:2605.20234v1 Announce Type: new Abstract: Prior-Data Fitted networks (PFNs) have been very successful in tabular contexts, handling prediction tasks in context. However, they are designed for si
arXiv:2509.07674v2 Announce Type: replace Abstract: Explainability, in particular, the ability for robots to explain why they have made a decision or behaved in a certain way, is a critical tool in he
arXiv:2410.18915v4 Announce Type: replace-cross Abstract: Consider two problems about an unknown probability distribution p: 1. How many samples from p are required to test if p is supported on n elem
arXiv:2605.21318v1 Announce Type: new Abstract: Large language models (LLMs) are highly sensitive to the prompts used to specify task objectives and behavioral constraints. Many recent prompt optimiza
arXiv:2605.20749v1 Announce Type: new Abstract: Gated Linear Units (GLU) and their variants are widely adopted in modern open-source large language model architectures and consistently outperform thei
arXiv:2605.20745v1 Announce Type: cross Abstract: Generative verifiers have emerged as a promising paradigm for step-wise verification, but their verification behavior is often poorly calibrated: they
The new issue of Daedalus, the open-access Journal of the American Academy of Arts and Sciences, is chock full of good material on AI. w/@demishassabis @ylecun @alondra @pushmeet and so many others I
arXiv:2605.20946v1 Announce Type: new Abstract: The thinking-while-speaking paradigm aims to make AI communication more human. A key challenge is maintaining fluent speech while performing deep reason
This New York Times piece is worth your time. Here’s what is happening, as simply as I can put it. Back in January, Trump sued the IRS, an agency he controls, demanding 10 billion over the leak of his
This New York Times piece on the January 6th slush fund is worth your time. Here’s what is happening, as simply as I can put it. Back in January, Trump sued the IRS, an agency he controls, demanding 1
arXiv:2605.20309v1 Announce Type: new Abstract: Current personalization methods for generative vision models typically encode new concepts through continuous adapters or weight updates, yet provide li
arXiv:2605.21442v1 Announce Type: new Abstract: Modern LLMs typically require multistage training pipelines to achieve strong downstream performance, with post-training serving as the main interface f
arXiv:2605.20973v1 Announce Type: new Abstract: The effectiveness of rock support in underground mines depends on the interaction between installed rock bolts and the structural fabric of the surround
arXiv:2605.21299v1 Announce Type: new Abstract: Humans effortlessly go beyond literal meanings: If you mow the lawn, I will give you fifty dollars, is typically understood as implying that the speaker
arXiv:2605.20292v1 Announce Type: new Abstract: Numerical time-series models can effectively process irregular electronic health record (EHR) trajectories, but they do not naturally expose the measure
arXiv:2605.20581v1 Announce Type: new Abstract: Machine learning interatomic potentials (MLIPs) achieve excellent accuracy when trained on large Density Functional Theory (DFT) data. To be useful in p
Trump’s latest corruption seems to breach the constitution, creating a $1.8 billion slush fund for his friends without congressional authorization and effectively pardoning himself by stopping IRS aud
Trump’s use of taxpayer money to create a $1.8 billion political slush fund may be the episode of presidential corruption that is the most blatant and threatening to the constitutional order in modern
arXiv:2605.20543v1 Announce Type: new Abstract: Accurate vessel segmentation is essential for medical image analysis, yet remains challenging due to complex vascular patterns and imaging ambiguity. Mo
arXiv:2605.20461v1 Announce Type: new Abstract: Accurate polyp size stratification guides surveillance decisions, with lesions larger than 5 mm typically requiring closer follow-up. However, monocular
arXiv:2605.21487v1 Announce Type: new Abstract: Currently, enhancing Unified Multimodal Models (UMMs) with image understanding, generation, and editing capabilities mainly relies on mixed multi-task t
arXiv:2504.13109v2 Announce Type: replace Abstract: Flow matching models have emerged as a strong alternative to diffusion models, but existing inversion and editing methods designed for diffusion are
arXiv:2605.21131v1 Announce Type: new Abstract: Recent feed-forward models have significantly advanced geometry perception for inferring dense 3D structure from sensor observations. However, its essen
arXiv:2605.20599v1 Announce Type: new Abstract: This study presents a comprehensive approach for the clustering and classification of upper-limb surface electromyography (sEMG) signals during function
arXiv:2605.21094v1 Announce Type: new Abstract: We investigate unpaired image inverse problems, a challenging setting where only independent, non-paired sets of noisy measurements and clean target sig
arXiv:2605.20838v1 Announce Type: new Abstract: Several large-scale video datasets have been published these years and have advanced the area of video understanding. However, the newly emerged user-ge
arXiv:2605.21489v1 Announce Type: cross Abstract: Pretrained diffusion models serve as frozen teachers feeding downstream pipelines such as text-to-3D, single-step distillation, and data attribution.
Vega turns a full credential into a single proof, sharing only what is needed and nothing more, with performance that works in real apps. The post Vega: Zero-knowledge proofs for digital identity in t
arXiv:2605.20772v1 Announce Type: new Abstract: While medical Multimodal Large Language Models (MLLMs) have shown promise in assisting diagnosis, they still frequently generate hallucinated responses
arXiv:2605.20291v1 Announce Type: new Abstract: Large language models (LLMs) have enabled web agents that follow natural language goals through multi-step browser interactions. However, agents fine-tu
What we find most useful about this study is the decomposition. For byte-level pretraining, the ordering is throughput first and boundary signal second; the boundary benefit can be recovered without a
arXiv:2601.18973v4 Announce Type: replace Abstract: Quantum hardware suffers from intrinsic device heterogeneity and environmental drift, forcing practitioners to choose between suboptimal non-adaptiv
arXiv:2605.20364v1 Announce Type: new Abstract: Automatic evaluation of long-form literary writing remains challenging, as generic LLM-as-Judge approaches may not fully capture creativity-related dime
Francois Chollet observes that AI systems which always affirm user correctness without nuance or disagreement reduce his confidence in their reliability. This reflects a concern that uncritical agreem
arXiv:2506.09521v2 Announce Type: replace-cross Abstract: Speaker anonymization systems hide the identity of speakers while preserving other information such as linguistic content and emotions. To eva
arXiv:2603.00995v2 Announce Type: replace-cross Abstract: The rapid progress in 6G communication and high-bandwidth radar has driven an unprecedented surge in the spatial density of signal sources, re
arXiv:2404.07106v2 Announce Type: replace Abstract: Point cloud completion aims to generate a complete and high-fidelity point cloud from an initially incomplete and low-quality input. A prevalent str
Nous Research announced four major performance upgrades to their Hermes Agents framework, aimed at improving speed and efficiency. The update, referred to as the `hermes update`, enables faster execut
arXiv:2605.19179v1 Announce Type: cross Abstract: We present a cloud-based tool that uses drones and machine learning to help recover instrumentally observed meteorite falls. We showcase a collection
arXiv:2605.19575v1 Announce Type: new Abstract: The article observes data analysis of 286 multi-word expressions (MWEs) based on 16 lexical, grammatical and other criteria described in theoretical boo
arXiv:2510.19382v2 Announce Type: replace-cross Abstract: Understanding the dynamics of feature learning in neural networks (NNs) remains a significant challenge. The work of (Mousavi-Hosseini et al.,
arXiv:2507.01932v2 Announce Type: replace-cross Abstract: We study a class of nonconvex-nonconcave minimax problems in which the inner maximization problem satisfies a local Kurdyka-Lojasiewicz (KL) c
arXiv:2605.19855v1 Announce Type: cross Abstract: Concept-based Explainable Artificial Intelligence (XAI) interprets deep learning models using human-understandable visual features (e.g., textures or
arXiv:2603.13609v2 Announce Type: replace Abstract: Despite progress in deep learning for shared micromobility demand prediction, the systematic design and statistical validation of temporal input str
arXiv:2605.19944v1 Announce Type: cross Abstract: While empirical scaling laws for LLM reasoning are well-documented, the theoretical mechanisms governing out-of-distribution (OOD) generalization rema
arXiv:2605.20033v1 Announce Type: new Abstract: Multimodal large language models often generate reasoning chains containing subtle errors that lead to incorrect answers. Current verification approache
arXiv:2601.20529v3 Announce Type: replace Abstract: Robotic prospecting for critical resources on the Moon, such as ilmenite, rare earth elements, and water ice, requires robust exploration methods gi
arXiv:2605.19306v1 Announce Type: new Abstract: We address the open problem of training hypernetworks for Controllable Pareto Front Learning (CPFL) under split feasibility conditions with rigorous the
arXiv:2605.19366v1 Announce Type: new Abstract: Environmental science plays a pivotal role in safeguarding ecosystems, a domain driven by large-scale, heterogeneous data. In the big data era, artifici
arXiv:2605.18804v1 Announce Type: cross Abstract: We propose Adaptive Multi-Scale Goodness Aggregation (AMSGA), a novel extension of the Forward-Forward (FF) algorithm designed to improve stability, r
arXiv:2511.10292v2 Announce Type: replace-cross Abstract: Large Vision-Language Models (LVLMs) typically process visual inputs as a prefix to the language decoder. As the model autoregressively genera
arXiv:2605.19483v1 Announce Type: new Abstract: Using recent works of one of the authors (VSB) on collapse in generative models and two time scale dynamics in stochastic gradient descent in high dimen
arXiv:2605.19794v1 Announce Type: cross Abstract: We present AffectAI-Capture, a protocol for collecting synchronized multimodal data in four-person meeting-like interactions, combining eye tracking,
arXiv:2605.19950v1 Announce Type: new Abstract: Humans infer emotions by integrating observed multimodal cues with expectations about how affective states may unfold. Existing multimodal large languag
arXiv:2605.18762v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) is widely used to augment large language models with external knowledge retrieval to improve reliability and gene
arXiv:2604.19892v1 Announce Type: cross Abstract: Incremental Potential Contact (IPC) guarantees intersection-free simulation but suffers from high computational costs due to the expensive Hessian ass