Knowledge catalogue
arXiv:2603.07433v2 Announce Type: replace-cross Abstract: Dynamic Data selection aims to accelerate training by prioritizing informative samples during online training. However, existing methods typic
Liquid cooling system startup Iceotope Technologies Ltd. said today it has closed on a 26 million Series B round of funding as it strives to accelerate the adoption of its data center-focused hardware
arXiv:2605.12906v1 Announce Type: cross Abstract: Data selection during supervised fine-tuning (SFT) can critically change the behavior of large language models (LLMs). Although existing work has stud
arXiv:2603.10305v3 Announce Type: replace Abstract: Machine learning models can represent climate processes that are nonlocal in horizontal space, height, and time, often by combining information acro
Financial services companies have unique needs when it comes to business AI. They operate in one of the most highly regulated sectors while responding to external events that are updated by the second
Release: datasette-ip-rate-limit 0.1a0 The datasette.io site was being hammered by poorly-behaved crawlers, so I had Codex (GPT-5.5 xhigh) build a configurable rate limiting plugin to block IPs that w
arXiv:2509.19538v2 Announce Type: replace-cross Abstract: Diffusion-based world models have demonstrated strong capabilities in synthesizing realistic long-horizon trajectories for offline reinforceme
Dear AI labs, A neverending black and white kanban board modeled after Jira (no offense) is not what we want as the future of work. Give me flexibility. Give me delight. Give me color. Please create t
arXiv:2605.12952v1 Announce Type: new Abstract: Grad-ECLIP is published at ICML 2024 and represents a new Transformer interpretation technical route (intermediate features-based). First, this paper de
arXiv:2602.22847v2 Announce Type: replace-cross Abstract: The concept of ranking aggregation plays a central role in preference analysis, and numerous algorithms for calculating median rankings, often
arXiv:2605.12840v1 Announce Type: cross Abstract: Marketplace platforms routinely evaluate pricing and allocation policies using logged observational data, yet strong offline performance does not impl
arXiv:2605.12983v1 Announce Type: new Abstract: Decision tree learning has long been a central topic in theoretical computer science, driven by its practical importance. A fundamental and widely used
arXiv:2605.13540v1 Announce Type: cross Abstract: Dynamic graphs are ubiquitous in real-world systems, and building generalizable dynamic Graph Foundation Models has become a frontier in graph learnin
arXiv:2603.22273v4 Announce Type: replace Abstract: The process of discovery requires active exploration -- the act of collecting new and informative data. However, efficient autonomous exploration re
arXiv:2601.00417v3 Announce Type: replace-cross Abstract: Transformer residual streams evolve by additive accumulation: each layer appends a feature update to a shared hidden state, but has no direct
arXiv:2605.13612v1 Announce Type: new Abstract: Understanding how deep neural networks learn useful internal representations from data remains a central open problem in the theory of deep learning. We
deepagents v0.6 is our biggest release yet!!! it’s all about perf - at the model layer w harness profiles, agent layer w code interpreter, and at scale w streaming and delta channels context hub backe
arXiv:2502.20427v3 Announce Type: replace-cross Abstract: Deepfakes - manipulated or forged audio and video media - pose significant security risks to individuals, organizations, and society at large.
arXiv:2605.13619v1 Announce Type: cross Abstract: Extended depth of field microscopy encodes axial information into a single acquisition through engineered point spread functions, but conventional and
Nous Research announced that Deepseek V4 Flash is temporarily available for free access through the Nous Portal, courtesy of Nous Research in collaboration with @novita_labs. This limited-time offer p
Deepseek V4 Flash is one of the best 'worker' models out there IMHO so this is very cool! Yet ANOTHER free model available through the Nous Portal 😍😍😍 Can't believe people are still playing with toy l
arXiv:2603.20521v2 Announce Type: replace-cross Abstract: Distributed reinforcement learning trains on data from stale, buggy, or mismatched actors, producing actions with high surprisal (negative log
arXiv:2605.13287v1 Announce Type: cross Abstract: Most exploration algorithms search broadly until uncertainty is resolved. When the action space is too large to resolve within budget, practitioners d
arXiv:2605.13769v1 Announce Type: cross Abstract: We study dense and mixture-of-experts (MoE) transformers in a tiny-scale pretraining regime under a shared LLaMA-style decoder training recipe. The sp
arXiv:2509.25781v2 Announce Type: replace Abstract: We address the issue of defining a semantics for deontic argumentation that supports weak permission. Some recent results show that grounded semanti
arXiv:2605.12874v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) are now standard tools for decomposing language model activations into interpretable features, and automated interpretability
arXiv:2605.13613v1 Announce Type: new Abstract: In this paper, we discuss a novel continuum robot design that enables the online tuning of the magnetic response at its tip. The proposed method allows
arXiv:2605.13790v1 Announce Type: cross Abstract: Partial differential equations (PDEs) are fundamental for modeling complex natural and physical phenomena. In many real-world applications, however, o
DID SOMEONE SAY FREE TOKENS IN FLEET???? Yes it's true. Fleet now has a built in model powered by @FireworksAI_HQ that's free for all Developer & Plus plan users. Try it out today (or before @hwchase1
arXiv:2605.12522v1 Announce Type: cross Abstract: Diffusion language models (DLMs) are promising alternatives to autoregressive language models (ARMs), yet the intrinsic differences in their generated
different tech terms and their closest emotion in english (vector similarity) you'll notice cryptocurrency being close to trust, which could be because both trust and lack of trust are often discussed
arXiv:2512.13399v2 Announce Type: replace Abstract: Crafting effective reward signals remains a central challenge in Reinforcement Learning (RL), especially for complex reasoning tasks. Existing autom
arXiv:2605.13282v1 Announce Type: new Abstract: Classical planners can effectively solve very large deterministic MDPs represented in STRIPS or PDDL where states are sets of atoms over objects and rel
arXiv:2511.01303v2 Announce Type: replace-cross Abstract: We consider the problem of constructing differentially private nonparametric confidence intervals (CIs) for an arbitrary quantity using resamp
arXiv:2605.13182v1 Announce Type: new Abstract: Diffusion-based models have shown strong performance in video super-resolution (VSR) and video frame interpolation (VFI). However, their role in the cou
arXiv:2602.08920v2 Announce Type: replace Abstract: Uncertainty calibration in pre-trained transformers is critical for their reliable deployment in risk-sensitive applications. Yet, most existing pre
arXiv:2602.06021v2 Announce Type: replace-cross Abstract: We study a data-dependent notion of diffusion-model generalization: when a model does not memorize the training set, where do its generated sa
arXiv:2605.13115v1 Announce Type: cross Abstract: Diffusion models depend on pseudo-random number generators (PRNGs) for latent noise sampling. We present DiffusionHijack, a supply-chain backdoor atta
arXiv:2605.12832v1 Announce Type: cross Abstract: Single-arm trials are an important study design for evaluating drug efficacy and safety without enrolling patients into a control arm. Although they d
arXiv:2605.12939v1 Announce Type: new Abstract: Recent diffusion- and flow-based VTON methods achieve strong results with pretrained generative models, but their reliance on multi-step sampling incurs
arXiv:2605.12702v1 Announce Type: new Abstract: General-purpose safety benchmarks for large language models do not adequately evaluate disability-related harms. We introduce DisaBench: a taxonomy of t
arXiv:2605.13708v1 Announce Type: cross Abstract: Federated learning enables collaborative model training across distributed clients, yet vanilla FL exposes client updates to the central server. Secur
.@Discoplomacy This kill-switch provision helps govt intervene in cases where UK datacenters are being maliciously used by a threat actor to conduct cyberattacks. It also helps in cases where the gove
arXiv:2602.03429v2 Announce Type: replace Abstract: To handle ambiguous and open-ended requests, Large Language Models (LLMs) are increasingly trained to interact with users to surface intents they ha
arXiv:2605.13484v1 Announce Type: cross Abstract: Calibration is commonly evaluated by comparing model confidence with its empirical correctness, implicitly treating reliability as a function of the c
arXiv:2605.13296v1 Announce Type: new Abstract: Multi-Agent Path Finding (MAPF) is a coordination problem that requires computing globally consistent, collision-free trajectories from individual start
arXiv:2605.12805v1 Announce Type: cross Abstract: MeanFlow enables one-step generation in continuous spaces by learning an average velocity over a time interval rather than the instantaneous velocity
arXiv:2605.12836v1 Announce Type: new Abstract: Continuous diffusion is a natural framework for non-autoregressive generation but has generally lagged behind masked discrete diffusion models (MDMs) on
arXiv:2605.13731v1 Announce Type: new Abstract: Generative artificial intelligence (AI) is increasingly being integrated into education, where it can boost learners' performance. However, these uses d
arXiv:2605.12574v1 Announce Type: cross Abstract: Vision-language models (VLMs) are trained on large-scale image-text corpora that may contain private, copyrighted, or otherwise sensitive data, motiva
arXiv:2602.06713v2 Announce Type: replace-cross Abstract: Missing data imputation, where a model is trained on observed data to estimate unobserved values, is a fundamental problem in machine learning
arXiv:2605.12974v1 Announce Type: new Abstract: In this work, we study how to ensure probabilistic safety for nonlinear systems under distributional ambiguity. Our approach builds on a backup-based sa
arXiv:2605.12649v1 Announce Type: new Abstract: Dataset distillation aims to synthesize a compact proxy dataset that is unreadable or non-raw from the original dataset for privacy protection and highl
arXiv:2605.13332v1 Announce Type: new Abstract: Argumentation is an important topic of AI for modelling and reasoning about arguments. In abstract argumentation, we consider directed graphs, so-called
arXiv:2509.13316v4 Announce Type: replace-cross Abstract: Recent interpretability methods have proposed to translate LLM internal representations into natural language descriptions using a second verb
arXiv:2605.12673v1 Announce Type: new Abstract: Agent benchmarks have become the de facto measure of frontier AI competence, guiding model selection, investment, and deployment. However, reward hackin
arXiv:2605.12701v1 Announce Type: cross Abstract: Machine learning algorithms in socially sensitive domains (e.g., credit decisions) often focus on equalizing predictive outcomes. However, satisfying
arXiv:2605.13175v1 Announce Type: new Abstract: Recent works have proposed incorporating heavy-tailed (HT) noise into diffusion- and flow-based generative models, with the goals of better recovering t
arXiv:2605.12623v1 Announce Type: cross Abstract: Multilingual document understanding remains limited for low-resource languages due to scarce training data and model-based annotation pipelines that p
arXiv:2605.13179v1 Announce Type: new Abstract: The Engram module -- a hash-keyed, O(1) associative memory injected into Transformer layers -- was recently shown to improve large language model pretra