Knowledge catalogue
arXiv:2605.00416v1 Announce Type: new Abstract: Generalist robot policies increasingly benefit from large-scale pretraining, but offline data alone is insufficient for robust real-world deployment. De
Pieter Haeck / Politico: Legislators and experts criticize the EU's €20B sovereign compute data center plan, questioning whether there is demand and the plan's reliance on Nvidia GPUs — Critics argue
arXiv:2605.00809v1 Announce Type: new Abstract: In this paper, we present extbf{Gen}erative extbf{L}anguage-extbf{I}mage extbf{P}re-training (GenLIP), a minimalist generative pretraining framework for
arXiv:2605.00480v1 Announce Type: new Abstract: Active learning aims to reduce annotation cost by selectively querying informative samples for supervision under a limited labeling budget. In this work
arXiv:2505.22003v2 Announce Type: replace Abstract: In India, access to legal assistance for the general public has been observed to have a critical gap, as many citizens are not able to take full adv
Yohei Nakajima highlights an impressive shader featured on a website's bottom-right card as an example of meticulous attention to detail in design and development. The post emphasizes how even small,
arXiv:2605.00434v1 Announce Type: new Abstract: Real-world multimodal learning is often hindered by missing modalities. While Incomplete Multimodal Learning (IML) has gained traction, existing methods
arXiv:2605.00556v1 Announce Type: cross Abstract: Partial driving automation creates a tension: drivers remain legally responsible for vehicle behaviour, yet their active control is significantly redu
Literally been saying this for years. @ylecun (who once trashed me for saying stuff like this) has become a carbon copy of me. He has done this so regularly, and without acknowledgement, that it has b
Llamacpp, when properly configured on Apple Silicon hardware, demonstrates robust performance and reliability for running language models. The tool can handle varied input requests effectively, making
arXiv:2509.24496v3 Announce Type: replace Abstract: The explosive growth of large language models (LLMs) has created a vast but opaque landscape: millions of models exist, yet their evolutionary relat
arXiv:2605.00505v1 Announce Type: cross Abstract: Modern information retrieval (IR) is no longer consumed primarily by humans but increasingly by large language models (LLMs) via retrieval-augmented g
arXiv:2512.04341v3 Announce Type: replace Abstract: Popular offline reinforcement learning (RL) methods rely on explicit conservatism, penalizing out-of-dataset actions or restricting rollout horizons
arXiv:2605.00253v1 Announce Type: new Abstract: Mamba's recurrent state h_t is, by construction, a compressed summary of every token seen so far. This raises a tempting hypothesis: if we extract token
arXiv:2605.00244v1 Announce Type: cross Abstract: We introduce Lucid-XR, a generative data engine for creating diverse and realistic-looking multi-modal data to train real-world robotic systems. At th
This podcast episode from Last Week in AI discusses recent developments in large language models, including updates on GPT 5.5 and DeepSeek V4, while also covering concerns about potential sabotage or
arXiv:2605.00398v1 Announce Type: new Abstract: Causal graph discovery for space-time systems is challenging in high-dimensional gridded data, which often has many more grid cells than temporal observ
arXiv:2605.00242v1 Announce Type: new Abstract: Millimetre-wave (mmWave) radar offers a more privacy-preserving alternative to RGB-based human pose estimation. However, existing methods typically rely
arXiv:2605.00789v1 Announce Type: new Abstract: Key-Value (KV) cache has become a de facto component of modern Large Vision-Language Models (LVLMs) for inference. While it enhances decoding efficiency
arXiv:2605.00342v1 Announce Type: new Abstract: Tree-based speculative decoding accelerates autoregressive generation by verifying multiple draft candidates in parallel, but this advantage weakens for
arXiv:2605.00781v1 Announce Type: new Abstract: 3D world generation is essential for applications such as immersive content creation or autonomous driving simulation. Recent advances in 3D world gener
arXiv:2605.00201v1 Announce Type: cross Abstract: The standard oracle model for matroid algorithms assumes that each independence query can be answered in constant time, regardless of the size of the
I cannot provide a summary for this entry as the post content appears incomplete or corrupted in the provided information. The title is cut off mid-sentence and doesn't clearly convey the full topic.
arXiv:2501.14660v2 Announce Type: replace-cross Abstract: In this work, we study the asymptotic behavior of Mixture of Experts (MoE) trained via gradient flow on supervised learning problems. Our main
arXiv:2604.01707v2 Announce Type: replace Abstract: Memory emerges as the core module in the large language model (LLM)-based agents for long-horizon complex tasks (e.g., multi-turn dialogue, game pla
arXiv:2510.17281v5 Announce Type: replace Abstract: Scaling up data, parameters, and test-time computation has been the mainstream methods to improve LLM systems (LLMsys), but their upper bounds are a
arXiv:2605.00356v1 Announce Type: new Abstract: Long-term conversational agents must decide which turns to store in external memory, yet recent systems rely on autoregressive LLM generation at every t
arXiv:2605.00762v1 Announce Type: new Abstract: We propose a new framework for meritocratic fairness in budgeted combinatorial multi-armed bandits with full-bandit feedback (BCMAB-FBF). Unlike semi-ba
arXiv:2605.00394v1 Announce Type: new Abstract: We present Mesh Field Theory (MeshFT) and its neural realization, MeshFT-Net: a structure-preserving framework for mesh-based continuum physics that cle
Meta is planning to power its AI data centers with solar energy beamed from space. If it works, solar farms could produce power 24/7 without batteries or backup generators. The company behind it all i
arXiv:2510.23557v2 Announce Type: replace-cross Abstract: Training or fine-tuning large language model (LLM)-based systems often requires costly human feedback, yet there is limited understanding of h
arXiv:2605.00397v1 Announce Type: new Abstract: We present MiniVLA-Nav v1, a simulation dataset for Language-Conditioned Object Approach (LCOA) navigation: given a short natural-language instruction,
MIT engineers have developed a 'computational violin' that uses physics-based simulation to realistically produce violin sound by modeling how the instrument and its vibrating strings interact with su
arXiv:2505.23723v2 Announce Type: replace Abstract: The emergence of large language model (LLM)-based agents has significantly advanced the development of autonomous machine learning (ML) engineering.
arXiv:2605.00689v1 Announce Type: new Abstract: As Large Language Models (LLMs) are increasingly deployed in cross-linguistic contexts, ensuring safety in diverse regulatory and cultural environments
arXiv:2605.00495v1 Announce Type: cross Abstract: Recent advances in multimodal generation have enabled high-quality audio generation from silent videos. Practical applications, such as sound producti
arXiv:2605.00431v1 Announce Type: cross Abstract: Although recent video-to-audio (V2A) models excelled at synthesizing semantically plausible sounds from visual inputs, they do not explicitly model ro
arXiv:2605.00025v1 Announce Type: cross Abstract: Speech neuroprosthesis systems decode intended speech from neural activity in the absence of audible output, offering a path to restoring communicatio
arXiv:2605.00393v1 Announce Type: new Abstract: Reinforcement learning (RL) in large environments often suffers from severe computational bottlenecks, as conventional regret minimization algorithms re
arXiv:2605.00764v1 Announce Type: new Abstract: Urban perception describes how people subjectively evaluate urban environments, shaping how cities are experienced and understood. Existing computationa
AI compute resources should not be treated as interchangeable commodities, as different hardware configurations, providers, and architectures significantly impact training costs, inference latency, an
Most AI today is passive. You prompt it, it responds, you prompt again. @origoshen , Co-CEO of @AI21Labs, draws a clear line between that reality and the agentic AI everyone's picturing. The direction
arXiv:2605.00475v1 Announce Type: cross Abstract: Real-world fine manipulation, particularly in bimanual manipulation, typically requires low-latency control and stable visual localization, while coll
arXiv:2605.00527v1 Announce Type: cross Abstract: Lissajous confocal laser endomicroscopy (CLE) is a promising solution for high speed in vivo optical biopsy for handheld scenarios. However, Lissajous
Bloomberg: Musk v. Altman: Greg Brockman testifies that his OpenAI stake is now worth ~30B; a Musk attorney asks why he hasn't donated 29B to OpenAI's nonprofit arm — OpenAI co-founder and President G
In his landmark trial against OpenAI CEO Sam Altman, Elon Musk testified that he was deceived into funding the company , and argued he was trying to save OpenAI's mission to develop AI safely by resto
arXiv:2405.13693v4 Announce Type: replace Abstract: Testing for individual discrimination involves deriving a profile, the comparator, similar to the one making the discrimination claim, the complaina
My surprise here seems warranted, this paper was retracted (There are other peer-reviewed meta-analyses of the impact of AI on education finding positive effects, like: https://www.researchgate.net/pu
arXiv:2605.00473v1 Announce Type: new Abstract: Multi-task learning (MTL) has emerged as a pivotal paradigm in machine learning by leveraging shared structures across multiple related tasks. Despite i
Bloomberg: Nearly 20 US state-run health insurance exchanges include ad trackers that send user data like race and citizenship info to companies like Meta, TikTok, Google — Nearly all of the 20 state-
arXiv:2605.00169v1 Announce Type: cross Abstract: Network digital twins (NDTs) are transforming network management by offering precise virtual replicas of physical network systems. However, their reli
Diana Novak Jones / Reuters: New Mexico child safety trial: New Mexico asks a judge to declare Meta a public nuisance and to order it to pay $3.7B and overhaul its apps to protect children — The U.S.
NEW paper from Sakana AI (ICLR 2026). A 7B Conductor model just hit SOTA on GPQA-Diamond and LiveCodeBench by orchestrating other LLMs instead of solving problems itself. (great paper! bookmark it!) T
New Redis data type just dropped - arrays, accessible by index, with a new text grep search mechanism [blog post] Redis array: short story of a long development process => https://antirez.com/news/164
Yohei Nakajima shared an informal post on X expressing enjoyment in creating a video, likely showcasing a project or creative work. The post reflects a personal commentary on the creative process rath
arXiv:2605.00260v1 Announce Type: new Abstract: Nonlinear Parametric Optimization Network (NLPOpt-Net) is an unsupervised learning architecture to solve constrained nonlinear programs (NLP). Given the
No longer are Fleet agents constrained to a single model. With multi-model support, you can build more efficient agents at scale http://langchain.com/langsmith/fleet Not every step in an agent workflo
arXiv:2605.00751v1 Announce Type: new Abstract: Monte Carlo Tree Search (MCTS) scales poorly in cooperative multi-agent domains because expansion must consider an exponentially large set of joint acti
arXiv:2605.00086v1 Announce Type: new Abstract: High-quality corpora are essential for advancing Natural Language Processing (NLP) in Portuguese. Building on previous encoder-only models such as BERTi
Not every step in an agent workflow needs the same model. Fleet now lets you customize which model each sub-agent uses, so you can route simple tasks to fast/cheap models and keep stronger models for