Knowledge catalogue
arXiv:2605.11182v2 Announce Type: replace Abstract: On-policy distillation (OPD) and on-policy self-distillation (OPSD) have emerged as promising post-training methods for large language models, offer
arXiv:2509.14250v2 Announce Type: replace Abstract: This paper explores prompts and prompting in large language models (LLMs) as dynamic semiotic phenomena, drawing on Peirce's triadic model of signs,
arXiv:2411.00934v2 Announce Type: replace-cross Abstract: Visual content on social media has become increasingly influential in shaping political discourse and civic engagement, but it also limits par
arXiv:2605.24411v1 Announce Type: new Abstract: Existing language model applications struggle to meet the demand for emotionally oriented support, primarily due to their inability to maintain deep, pe
arXiv:2605.23918v1 Announce Type: cross Abstract: The AI inference industry keeps models loaded in GPU memory around the clock to avoid cold-start latency, implicitly treating idle power as a fixed co
arXiv:2605.24556v1 Announce Type: cross Abstract: Multilingual retrieval increasingly underpins cross-lingual question answering and retrieval-augmented generation. Strong zero-shot scores on multilin
The near impossible is becoming possible. We are building toward a sustained human presence at the lunar South Pole. It begins with Phase 1: CLPS landers and LTV rovers testing the “science of surviva
arXiv:2605.24477v1 Announce Type: new Abstract: The Normalized Maximum Likelihood (NML) codelength, or stochastic complexity, represents a principled criterion for universal coding. While recent coare
An OpenAI insider (@thsottiaux) raises concerns about the risks of over-relying on AI agents to handle cognitive tasks, warning against wholesale delegation of thinking to autonomous systems. The warn
arXiv:2605.24697v1 Announce Type: cross Abstract: Diffusion large language models promise faster generation by refining many token positions in parallel, but this parallelism introduces a hidden contr
arXiv:2605.24782v1 Announce Type: new Abstract: While Vision Foundation Models (VFMs) excel at predictive tasks on satellite imagery, their performance can arise from visual correlations rather than u
The pressure Daniel Stenberg on the unprecedented level of pressure the curl team are facing right now thanks to the deluge of (credible) AI-assisted security issues being reported. The rate of incomi
arXiv:2605.25880v1 Announce Type: new Abstract: Large-scale transformer training and deployment are increasingly constrained by the transfer of activations, gradients, and optimizer states across acce
The road to Hell is paved with closed-source citadels disguised as good intentions. The Pope is right: AI takes on the characteristics of those who build it, finance it, and regulate it. So the questi
The Rogue. A film I’ve been trying to make for more than ten years. This project pushed me creatively more than anything I’ve ever done. and I truly believe this is going to become a pivot moment for
The SpaceX IPO is a shitshow. When you peel back the layers, you realize how thoroughly corrupt it is. SpaceX’s unconventional corporate arrangements appear to benefit Elon Musk at the expense of othe
The Telegraph: Macron tore up 65 years of doctrine to defend Europe with French nukes, with or without the US. Poland, Germany, the Netherlands, Belgium, Greece, Sweden, Denmark, and now the Czech Rep
arXiv:2605.24096v1 Announce Type: cross Abstract: Core systems like key-value stores have historically taken years to build, and are designed to be general so as to amortize cost across deployments, p
arXiv:2605.25868v1 Announce Type: cross Abstract: The speed and accuracy of an artificial teammate fundamentally alter the failure states of Human-AI integration. While high-speed AI interventions ris
arXiv:2605.24718v1 Announce Type: new Abstract: Tokenizer fertility the number of tokens per word imposes a hidden cost on non-English NLP. We measure fertility for ten foundation models across 25 Eur
arXiv:2605.25134v1 Announce Type: cross Abstract: Sparse optimization is a fundamental challenge in various practical applications. A popular approach to sparse optimization is ell_p regularization. H
There are two ways to add login to your app on Replit: → Replit Auth: zero setup, users sign in with their Replit account → Clerk Auth: your own branded sign-in, dev/prod environments both take one pr
arXiv:2605.25208v1 Announce Type: new Abstract: Emotion-Cause Pair Extraction (ECPE) was introduced to explain why an emotion occurs, but this goal is now often reduced to binary pair/non-pair predict
this basically destroys the extrapolations that had Anthropic making two trillion dollars a year. It's clear that growth for coding tools such as Claude Code has decelerated from the pace it was since
This is our mission. The timeline for achieving this shrinks significantly if we can 10-100x the useful output of our engineering and manufacturing teams. AI and robotics make this possible. This can
this logic from 2024 held up pretty well considering all that’s changed. 9 reasons that OpenAI could someday be seen as the WeWork of AI: 👉 Lots of competitors are catching up. 👉 OpenAI has been force
arXiv:2605.25850v1 Announce Type: cross Abstract: This paper investigates large language model (LLM) abstention learning, specifically using ternary reward, which incentivize truthfulness in large lan
arXiv:2605.24489v1 Announce Type: new Abstract: Enzyme-reaction retrieval is a fundamental problem in computational biology, underpinning enzyme characterization, reaction mechanism elucidation, and t
Elon Musk expressed enthusiasm on X (formerly Twitter) about constructing a major lunar base, reflecting his vision for SpaceX's long-term goals of sustained human presence on the Moon. The post likel
arXiv:2603.06687v2 Announce Type: replace-cross Abstract: Geo-temporal understanding, the ability to infer location, time, and contextual properties from visual input alone, underpins applications suc
TinkerAPI, developed by TML, is a post-training infrastructure tool that Soumith Chintala recommends as an essential component for new AI companies during their startup phase. The tool appears to addr
arXiv:2605.24846v1 Announce Type: cross Abstract: Large language models (LLMs) display strong comprehensive abilities, yet the internal mechanisms that support these behaviors remain insufficiently un
arXiv:2605.25046v1 Announce Type: cross Abstract: YOLO-series and DETR-based detectors struggle with tiny-object detection. YOLO-style models benefit from efficient dense prediction, but their large-s
Hugging Face has released 1-bit and Ternary Bonsai Image 4B, a new family of lightweight image-generation models optimized for efficient diffusion inference. These models are designed to deliver high-
Today's Training Data episode takes us BTS on the infrastructure challenges required to do large RL runs at scale, featuring @ellev3n11 (Composer Lead at @cursor_ai) and @dzhulgakov (Co-Founder at @Fi
arXiv:2605.25310v1 Announce Type: new Abstract: Tool-using LLM agents produce trajectories whose calls form a directed dependency graph: earlier tool outputs supply arguments to later calls. Whether t
arXiv:2507.10593v3 Announce Type: replace-cross Abstract: Every LLM tool call is structurally an RPC -- a function name, JSON arguments, and a serialized result -- yet each protocol (native Python, MC
arXiv:2605.25541v1 Announce Type: cross Abstract: Neural networks encode inputs as high-dimensional vectors, known as representations, that capture how models process data by encoding task-relevant st
arXiv:2602.23916v2 Announce Type: replace-cross Abstract: The advent of large-scale self-supervised learning (SSL) has produced a vast zoo of medical foundation models. However, selecting optimal medi
arXiv:2602.22631v2 Announce Type: replace-cross Abstract: Neural networks are increasingly deployed in scientific, safety critical, and mission critical pipelines, yet verification and analysis are of
arXiv:2605.25601v1 Announce Type: cross Abstract: Teacher education requires deliberate practice with learners who exhibit identifiable strengths, weaknesses, and partial mastery. Large language model
arXiv:2605.24238v1 Announce Type: new Abstract: In this paper, we advocate for incorporating enactive approaches to perception and cognition into artificial intelligence (AI). Enactive approaches view
arXiv:2605.23929v1 Announce Type: new Abstract: Modern AI systems increasingly rely on workflows composed of multiple interacting agents, some powered by large language models (LLMs) and others by con
arXiv:2605.24873v1 Announce Type: cross Abstract: Despite the importance of causal reasoning, training LLMs to reason causally remains underexplored. Existing data efforts mostly focus on benchmarking
arXiv:2509.04445v2 Announce Type: replace Abstract: Recent AI trends seek to align AI models to learned human-centric objectives, such as personal preferences, utility, or societal values. Using stand
arXiv:2605.25399v1 Announce Type: new Abstract: Objective: Survival analysis is central to medical prediction, yet large language models (LLMs) are rarely used as end-to-end survival models because ce
arXiv:2605.24213v1 Announce Type: cross Abstract: Evaluation harnesses are software systems that orchestrate model evaluation by managing model invocation, data loading, metric computation, and result
arXiv:2509.12672v2 Announce Type: replace Abstract: The volume of machine-generated content online has grown dramatically due to the widespread use of Large Language Models (LLMs), leading to new chal
arXiv:2605.24025v1 Announce Type: cross Abstract: Large models have delivered remarkable performance across a wide range of perception and generation tasks, yet practical deployment is increasingly co
arXiv:2602.01914v2 Announce Type: replace Abstract: Token attribution methods provide intuitive explanations for language model outputs by identifying causally important input tokens. However, as mode
arXiv:2605.24643v1 Announce Type: new Abstract: This paper presents reinforcement learning (RL) policies for dynamic quadrupedal locomotion in planetary exploration scenarios. Building on a taskoptimi
arXiv:2605.24953v1 Announce Type: new Abstract: Industrial asset operations and maintenance question answering is inherently multi-turn, iterative, and highly dependent on external tool invocation. Ho
arXiv:2605.25612v1 Announce Type: cross Abstract: The observation that activation sparsity emerges in MLP blocks of standardly trained Transformers offers an opportunity to drastically reduce computat
arXiv:2605.23989v1 Announce Type: new Abstract: Agentic AI systems -- Large Language Models (LLMs) augmented with planning, tool use, memory, and long-horizon interactions -- can execute complex tasks
arXiv:2603.09581v2 Announce Type: replace Abstract: Adam is a widely used optimization algorithm in deep learning, yet the specific class of objective functions where it exhibits inherent advantages r
arXiv:2605.24033v1 Announce Type: new Abstract: Mechanistic interpretability often identifies circuits inside Transformer models, but explanations of those circuits are usually validated through examp
arXiv:2605.24000v1 Announce Type: new Abstract: Toxicity in online gaming communities remains a persistent challenge, manifesting across genres, platforms, and player interactions. While much research
arXiv:2605.25038v1 Announce Type: new Abstract: Applied Behavior Analysis (ABA) is a clinical discipline whose documentation, teaching programs and multi-session behavioral logs, is formulaic and high
Trace data is literally worth its weight in gold these days, if you know what to do with it! As has been established, creating effective agents requires shipping early, observing behavior, and iterati
arXiv:2605.24079v1 Announce Type: cross Abstract: Data contamination is a known threat to the reliability of model evaluation. However, it remains underexplored in code large language models (LLMs), w