Knowledge catalogue
arXiv:2605.27140v1 Announce Type: new Abstract: Reinforcement learning for multi-turn agents suffers from a credit-assignment mismatch: rewards are sparse and trajectory-level, while success often hin
arXiv:2602.04599v2 Announce Type: replace Abstract: We propose stochastic decision horizons (SDH), a theoretically grounded framework for solving constrained RL problems with every-step constraint sat
arXiv:2605.14151v1 Announce Type: cross Abstract: We introduce a stochastic global optimization method based on random walks on Grassmannian manifolds. To minimize a continuous objective ell:R^drighta
arXiv:2605.26898v1 Announce Type: cross Abstract: Large Language Models (LLMs) can generate functional source code from natural-language prompts, but often fail to consistently follow higher-level arc
arXiv:2605.26523v1 Announce Type: cross Abstract: Large-batch Contrastive Learning (CL), the foundation of modern representation learning, is fundamentally incompatible with the volatile resource cons
Stronger models do not always need lighter harnesses. Everyone believes more structured harnesses universally improve reliability, and that higher-capability models need proportionally less structural
arXiv:2605.26429v1 Announce Type: cross Abstract: This paper addresses structured out-of-distribution (OOD) testing in high-stakes machine learning applications. Traditional conformal methods rely on
arXiv:2508.07996v2 Announce Type: replace Abstract: Group Activity Detection (GAD) involves recognizing social groups and their collective behaviors in videos. Vision Foundation Models (VFMs), like DI
arXiv:2601.06580v2 Announce Type: replace Abstract: Singlish is a creole rooted in Singapore's multilingual environment that continues to evolve alongside social and technological change. We examine d
Super happy that a bunch of people are finding marlin useful. Thank you for the inference support @ZeroGPU_AI @huggingface 🥰🤝 We’ve got hands on more compute now so we’ll also release a series of blog
arXiv:2511.04711v2 Announce Type: replace-cross Abstract: Large-scale vision-language models, especially CLIP, have demonstrated remarkable performance across diverse downstream tasks. Soft prompts, a
arXiv:2603.01327v2 Announce Type: replace-cross Abstract: Large language models (LLMs) exhibit strong performance on self-contained programming tasks. However, they still struggle with repository-leve
arXiv:2605.27245v1 Announce Type: new Abstract: Symbolic regression (SR) seeks closed-form mathematical expressions that fit observed data. Neural SR methods amortize the search by training an encoder
arXiv:2509.10481v2 Announce Type: replace-cross Abstract: Wireless communication is evolving into an agent era, where large-scale agents with inherent embodied intelligence are not just users but acti
arXiv:2605.26911v1 Announce Type: new Abstract: LLM-generated peer reviews are increasingly common at major venues, yet their deficiencies are hard to detect because they are uniformly fluent and well
arXiv:2510.04533v2 Announce Type: replace Abstract: Diffusion models achieve state-of-the-art image generation but often produce semantic inconsistencies, or hallucinations. Existing inference-time gu
arXiv:2601.05729v2 Announce Type: replace Abstract: Recent studies have demonstrated the efficacy of integrating Group Relative Policy Optimization (GRPO) into flow matching models, particularly for t
arXiv:2605.26628v1 Announce Type: new Abstract: This report describes Tail-Aware HiFloat4, our submission to the low-bit text-to-video generation quantization challenge. Our method adapts the public V
arXiv:2504.02775v2 Announce Type: replace Abstract: We aim to solve unsupervised anomaly detection in a practical challenging environment where the normal dataset is both contaminated with defective r
arXiv:2605.26436v1 Announce Type: cross Abstract: Discrete masked diffusion language models such as LLaDA generate text through iterative denoising, where mask tokens are progressively replaced with p
arXiv:2605.27167v1 Announce Type: new Abstract: Planning the motion path for a tightly coupled dual-arm space manipulator under closed-chain constraints is a fundamental yet challenging problem in on-
arXiv:2605.26984v1 Announce Type: new Abstract: Tax evasion causes severe losses of government revenues and disturbs the economic order of fair competition. To help alleviate this problem, the latest
arXiv:2605.26891v1 Announce Type: new Abstract: This paper presents a multilingual customer service self-help corpus comprising 1,122 manually validated documents in Finnish, Danish, Norwegian, and Sw
arXiv:2605.27239v1 Announce Type: new Abstract: Annotation quality is difficult to sustain when campaigns span weeks or months with small annotator pools. We present a Setswana sentiment dataset of 3,
Wall Street Journal: Temu owner PDD reports Q1 revenue up 11% YoY to ~15.7B, below ~16.2B est., net profit down 15% to ~1.85B, below ~3.4B est., amid fierce competition in China — The company is rolli
Tensormesh Inc. has hit upon a way to make artificial intelligence inference more efficient by eliminating the need for redundant computations, and its technology is so convincing that several of AI i
Bonsai Image 4B is a family of compressed image-generation models available in 1-bit and ternary variants that reduces the footprint of a modern 4B-class diffusion transformer by up to 8.3x while pres
arXiv:2605.25538v2 Announce Type: replace Abstract: Track materialization converts raw video into reusable object tracks that downstream queries can run against without rerunning tracking, but extract
Thank Heaven for the First Amendment in America! The truth is called hateful in Belgium. Therefore speaking it is against the law. This is more frightening than calling the truth 'misinformation'. The
arXiv:2601.07085v2 Announce Type: replace-cross Abstract: Large language model (LLM)-based conversational AI systems present a challenge to human cognition that current frameworks for understanding mi
How newsrooms should use AI - or if they should at all - has been a recurrent debate within the media industry over the last several years. Increasingly, these rules are being hammered out at the barg
Enterprise GPU access is expanding as Advanced Micro Devices Inc. lowers barriers with the air-cooled Instinct MI350P GPU and a ready-to-run software stack designed for standard enterprise servers. Th
arXiv:2605.26778v1 Announce Type: new Abstract: Retrieval-augmented generation promises to ground language model outputs in external evidence, yet the field has no reliable way to verify whether retri
The best research labs are building what comes after static models. Congrats to @trajectorylabs on the launch! Excited to have them training on the AI Native Cloud as they push the frontier on Continu
arXiv:2605.26246v1 Announce Type: new Abstract: Knowledge distillation (KD) transfers knowledge from a large teacher model to a smaller student. In language modeling, the student is trained either on
arXiv:2605.27176v1 Announce Type: new Abstract: Knowledge graphs (KGs) can provide structured scientific context to language models, but it remains unclear which graph facts actually shape the generat
arXiv:2605.26128v1 Announce Type: new Abstract: Production LLM systems increasingly require machine-readable outputs: JSON objects, typed traces, regex-constrained fields, and tool-call schemas. This
arXiv:2605.27220v1 Announce Type: new Abstract: In modern RAG pipelines, query augmentation methods such as HyDE and query expansion are applied to every query, resulting in substantial LLM inference
arXiv:2605.26346v1 Announce Type: new Abstract: Objective: To describe the design and early clinical evaluation of The Daily Dose (TDD), an LLM-driven, automated clinical summarization and clinical-tr
This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology. Stay on top of what’s going on in AI this summer Here at MIT T
The entire event yesterday, launching missions, landers, rovers, tech demos building a Moon Base, and sci-fi capabilities like MoonFall, brought to you by those who Dare Mighty Things. Just the very b
The fact that tokens went from something no one even put in a budget line a year ago to an absolute requirement for coding now is the cause of handwringing, not that AI is not turning out to be useful
“The future of AI is going to be local models running on extraordinary desktop hardware.” - @Jason This line from the recent @theallinpod hit hard. For years AI meant sending everything to the cloud,
the future of Continual Learning will rely on building to systems to ingest, understand, & apply knowledge from Agent Traces at scale had a blast presenting LangSmith Engine with @bentannyhill to show
arXiv:2605.26830v1 Announce Type: cross Abstract: State estimation is a fundamental problem in control and signal processing, for which the Kalman Filter provides an optimal solution under linear dyna
arXiv:2605.26670v1 Announce Type: cross Abstract: Sequential editing of structured knowledge in large language models allows targeted factual updates without retraining, yet existing methods often rel
arXiv:2605.26494v1 Announce Type: new Abstract: We introduce the MiniMax-M2 series, a family of Mixture-of-Experts language models built around the principle that mini activations can unleash maximum
The MiniMax M2 series was one of the most widely used open-weight LLM series earlier this year. Now, we got a technical report with some interesting tidbits. I summarized some of them below: 1. Full a
arXiv:2602.03238v2 Announce Type: replace Abstract: With the advent of Large Language Models (LLMs), general-purpose agents have seen fundamental advancements. However, evaluating these agents present
arXiv:2605.26711v1 Announce Type: new Abstract: We construct a binary mixed-regime process with one deterministic textual regime and one random regime governed by an unobserved latent state. Even an i
The open source community has been delivering on LTX 2.3 LoRAs. Fine tuning LTX 2.3 unlocks control that you can't get from closed models. Here are 7 LoRAs that can save your footage. There are too ma
On Monday, Pope Leo XIV unveiled an encyclical letter addressing the societal implications of artificial intelligence. The letter, titled Magnifica Humanitas, warned that the 'use of AI is never a pur
The Redpoint InfraRed 100 is now live. These are the companies building the infrastructure that powers everything happening in AI right now, from world models and agent runtimes to the sandboxes, data
arXiv:2605.26415v1 Announce Type: cross Abstract: Deploying Vision-Language Models on resource-constrained hardware typically requires INT8 quantization, but in joint-embedding architectures such as C
arXiv:2605.27163v1 Announce Type: new Abstract: In strategic classification, an institution (e.g., a bank) anticipates adaptation from users who change their features to increase utility in a classifi
arXiv:2605.26856v1 Announce Type: cross Abstract: Cognitive science remains split between cognitivism - which accounts for recursion and language but cannot ground formal symbols in meaning - and 4E a
Wall Street Journal: The Shanghai Stock Exchange says memory maker CXMT cleared a listing review for the exchange's Nasdaq-like STAR Board, in what could be China's top IPO in 2026 — The listing could
arXiv:2605.26489v1 Announce Type: new Abstract: Large language model pre-training typically exhibits a two-phase trajectory: a fast initial loss drop followed by a prolonged slow improvement. We ident
arXiv:2605.26872v1 Announce Type: cross Abstract: LLM training increasingly relies on teacher-generated supervision, from synthetic responses to reasoning traces and tool-use demonstrations. Current p
Chloe Taylor / CNBC: The UK's GCHQ head says the UK and allies have a “narrowing window” to counter cyber threats from China and Russia, as Russia intensifies “daily” hybrid warfare — Choose CNBC as y