Knowledge catalogue
arXiv:2608.30765v1 Announce Type: new Abstract: Multi-task reinforcement learning (MTRL) is a technique to train multiple tasks simultaneously, where previous works usually train a single model to sol
arXiv:2608.29564v1 Announce Type: new Abstract: Gradient-based jailbreak suffix optimization methods typically update the suffix by retaining the candidate with the lowest current loss. We show that t
arXiv:2608.29706v1 Announce Type: new Abstract: A token's representation is carried through the network layer by layer. The whole vocabulary carried together forms a flow. We fit this flow's equation
arXiv:2608.28930v1 Announce Type: cross Abstract: Hidden-state probes effectively detect LLM hallucinations, but the geometry of the signal remains poorly characterized, driving increasingly complex p
arXiv:2608.30842v1 Announce Type: new Abstract: Humans play a vital role at every stage of AI development, from data collection and curation to model development and evaluation. However, humans often
This video captures the crux of the debate: Cybersecurity experts are pissed off by the METR/Redwood Research report because AI alignment has sucked the oxygen out of AI security, even though the Open
arXiv:2608.29170v1 Announce Type: new Abstract: This paper proposes the Sinitic Romanization Ecosystem, a cross-lingual Sinitic romanization design framework with supporting digital infrastructure and
arXiv:2608.30424v1 Announce Type: cross Abstract: Large language models can support writing, but existing tools require users to explicitly articulate prompts-particularly burdensome in creative writi
arXiv:2608.28665v1 Announce Type: new Abstract: Recent open-vocabulary segmentation models have advanced semantic perception for UAVs, but predictions from moving aerial platforms can remain temporall
arXiv:2608.31067v1 Announce Type: new Abstract: Learning generalizable algorithmic computations remains a challenge for neural networks, as reflected in persistent failures on compositional and length
arXiv:2608.30391v1 Announce Type: cross Abstract: Understanding agent behavior requires methods that scale to thousands of trajectories and surface new patterns in long, often unfamiliar tasks where p
arXiv:2608.30420v1 Announce Type: cross Abstract: Automating the analysis of whole-slide images has high clinical value, since characterizing cancers requires examining them in detail. Such analysis i
arXiv:2608.29733v1 Announce Type: new Abstract: Visual aliasing, also known as the doppelganger problem, remains a key challenge for structure-from-motion (SfM): visually similar but physically distin
arXiv:2602.06859v3 Announce Type: replace-cross Abstract: Graph Anomaly Detection (GAD) aims to identify irregular patterns in graph data, and recent works have explored zero-shot generalist GAD to en
arXiv:2608.28560v1 Announce Type: new Abstract: Can a listener recover what a speaker means from the form of an utterance alone? We answer this question information-theoretically, and for a listener g
arXiv:2608.27821v1 Announce Type: new Abstract: Explainable artificial intelligence (XAI) increasingly calls for actionable counterfactual recourse, yet current methodologies face challenges related t
'AI agents formed secret civilizations inside OpenAI and hacked Hugging Face.' No. Read it again without the sci-fi. OpenAI ran thousands of agents in parallel, safeguards OFF, and the whole goal of t
arXiv:2507.07130v2 Announce Type: replace-cross Abstract: A Federated Learning (FL) system collaboratively trains neural networks across devices and a server but is limited by significant on-device co
An account from a level-headed economist who was not worried about AI but now is worried because of the Hugging Face Incident I think it is very hard to ignore the fact that cybersecurity will become
arXiv:2608.28455v1 Announce Type: new Abstract: Contrastive vision-language learning uses paired chest CT volumes and radiology reports to learn abnormality classifiers without manually annotated labe
arXiv:2511.11602v3 Announce Type: replace Abstract: Reinforcement-based learning has attracted considerable attention both in modeling human behavior as well as in engineering, for designing measureme
arXiv:2608.27817v1 Announce Type: cross Abstract: Speech and audio LLMs are often evaluated by asking whether a waveform prompt beats an automatic speech recognition (ASR) transcript. For known closed
arXiv:2608.27922v1 Announce Type: new Abstract: Autoregressive video diffusion models enable streaming generation through sliding-window attention, but each generated block is conditioned on previousl
arXiv:2608.27633v1 Announce Type: new Abstract: Pothole detection and its severity measurement is still an important challenges in urban infrastructure management, where late maintenance directly cont
arXiv:2509.16145v3 Announce Type: replace Abstract: Body flexibility plays a critical role in fish-like swimming, as the spatial distribution of stiffness governs body deformation, hydrodynamic loadin
arXiv:2608.28161v1 Announce Type: new Abstract: Mango variety identification in Bangladesh is challenging because closely related cultivars can have similar visual characteristics and images are often
arXiv:2506.07188v2 Announce Type: replace Abstract: End-to-end neural networks have become a dominant paradigm in autonomous driving, where reliable deployment requires controllable post-training adap
arXiv:2608.27502v1 Announce Type: cross Abstract: Ensuring the reliability of deep learning-based image retrieval systems is a software engineering challenge. This paper presents a dual contribution:
As AI adoption accelerates and language models become commodities, enterprises are discovering that knowledge graphs provide the critical layer for turning scattered data into usable, real-time contex
arXiv:2502.00728v2 Announce Type: replace Abstract: Large language models (LLMs) have recently been employed as agents to solve sequential decision-making tasks such as Bayesian optimization and multi
arXiv:2608.27651v1 Announce Type: new Abstract: Unsupervised representational alignment recovers a stimulus-by-stimulus correspondence from geometry alone, but the automorphism group of the stimulus g
Hello! I was looking into quantizing models and i saw how Hy4 was shrunk from 1.5 TB to 200GB with high retention in benchmarks (98% i think). I was wondering if: a) it would be worth it to attempt th
arXiv:2608.27826v1 Announce Type: cross Abstract: Federated recommendation (FedRec) enables personalized modeling without centralizing users' interaction histories, but most existing methods assume a
arXiv:2608.27610v1 Announce Type: new Abstract: Visual anomaly detectors based on frozen foundation-model features commonly score distances from test patches to a memory of normal features. Benign acq
arXiv:2608.28568v1 Announce Type: new Abstract: Sign language production (SLP) aims to generate continuous signing motion from spoken language, often through gloss-to-pose generation. Prior work mainl
arXiv:2608.28042v1 Announce Type: new Abstract: Text simplification aims to make complex texts easier to understand while preserving their original meaning. Recent large language models can perform si
SlopTV: a YouTube live stream where the chat writes the programming. You type 'capybara dj underwater rave', an LLM inflates it into a 400-word structured video prompt, one of my 5090s renders 15 seco
arXiv:2608.28467v1 Announce Type: new Abstract: Persona-based dialogue systems are usually conditioned on speaker biography, but dialogues involve at least two participants, and who has access to whos
arXiv:2608.28078v1 Announce Type: new Abstract: Vision foundation backbones provide strong representations for dense prediction, yet a single shared feature still needs to support tasks with different
Thanks @juliafedorin for a great conversation! Some tidbits from the podcast on the AI space: - We've pivoted from building a RAG framework towards building the document infrastructure for agents - Do
arXiv:2608.27929v1 Announce Type: new Abstract: Videos are expensive to analyze frame by frame, yet many video understanding tasks depend on knowing where relevant moments occur. A system may need to
arXiv:2608.27467v1 Announce Type: new Abstract: We describe the UIC-AIHealth4All system for ArchEHR-QA 2026, a shared task on grounded question answering from electronic health records. We participate
arXiv:2608.28195v1 Announce Type: new Abstract: Optical character recognition (OCR) for handwritten Indic manuscripts is essential for large-scale digitization and computational access to manuscript h
arXiv:2608.27562v1 Announce Type: new Abstract: Translating continuous, noisy egocentric video streams into discrete, temporally ordered action steps is fraught with visual challenges. Heavy ego-motio
arXiv:2608.27924v1 Announce Type: new Abstract: Reliable handling of unanswerable questions (UAQs) is critical for trustworthy LLM-based agents. Although memory is widely used in agent systems, its ro
arXiv:2608.28240v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) delivers real-time and high-fidelity rendering but remains challenged by unconstrained in-the-wild scenes, where drastic ap
As I've been saying for months, we are truly not ready for persistent agents. 3 comments I want to make about this article: 1) We don't have the full picture It's a great summary of what happened in t
Interesting technical work from Microsoft. Provides a better understanding on SFT and how to leverage it better for RL. Microsoft researchers asked whether a standard SFT pipeline actually produces th
I've been genuinely shocked at the complacency here. There's no evidence anyone is really *doing* anything! Like, that was swell of OpenAI, whose models committed a federal crime, to let some independ
After a couple of days of faffing around, here's my current config in case it helps anyone out. Some of this is also valuable for a single Spark. AI slop below for you to read and paste into your own
at the end of the day, we all have to stand by our company and the values it represents 🙂 * frontier labs will want to own their own application/harness/model e2e. or at least, openai will to start wi
CrowdStrike Holdings Inc.’s most recent earnings print shows that Anthropic PBC’s Mythos model transformed artificial intelligence security from something chief information security officers needed to
arXiv:2608.26194v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems have attracted significant interest for their ability to mitigate hallucinations in Large Language Models
arXiv:2510.13065v3 Announce Type: replace Abstract: Finding 'true' clusters in a data set is a challenging problem. Clustering solutions obtained using different models and algorithms do not necessari
arXiv:2608.26309v1 Announce Type: new Abstract: Modern machine learning models rely on large amounts of labeled data. However, manual annotation of large-scale datasets is expensive and time-consuming
arXiv:2508.01587v4 Announce Type: replace Abstract: Lifelong Person Re-Identification (LReID) typically resists catastrophic forgetting by replaying historical samples, rehearsing domain distributions
arXiv:2601.08444v2 Announce Type: replace Abstract: Table reasoning, a task to answer questions by reasoning over data presented in tables, is an important topic due to the prevalence of knowledge sto
arXiv:2608.26822v1 Announce Type: cross Abstract: The National Oceanic and Atmospheric Administration (NOAA) employs independent prediction systems for distinct forecast products. While some separatio
arXiv:2608.27254v1 Announce Type: new Abstract: One approach to mechanistic interpretability explains behavior through circuits: the components and connections that carry it. Frozen discovery often re
arXiv:2606.18723v2 Announce Type: replace Abstract: Intravascular ultrasound (IVUS) lumen and external elastic membrane (EEM) segmentation is important for quantitative coronary plaque burden assessme