Sliding-window beats linear attention
Interesting new paper from Alexia Jolicoeur-Martineau (of Tiny Recursive Model fame) and collaborators. They seem to be able to replace quadratic attention with sliding window attention + attention si
Knowledge catalogue
Interesting new paper from Alexia Jolicoeur-Martineau (of Tiny Recursive Model fame) and collaborators. They seem to be able to replace quadratic attention with sliding window attention + attention si
arXiv:2608.28444v1 Announce Type: new Abstract: Due to the nature of quadratic attention, Large Language Models (LLMs) consume a lot of memory and energy. Every new token costs more than the previous
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
https://huggingface.co/Nanbeige/Nanbeige4.2-3B-DSpark 4b model for the gpu poor that I think is stronger than qwen 3.5 9b now faster! I was getting roughly 35 t/s AR which was this models downside, it
arXiv:2511.14684v2 Announce Type: replace Abstract: Large language models (LLMs) often make reasoning errors when solving mathematical problems, and how to automatically detect and correct these error
Sori-1B is a 1B-parameter audio-language model built by a single SNU researcher whose core claim to fame is that its decoder is trained entirely from scratch on audio-paired text — no text-only pretra
arXiv:2608.27882v1 Announce Type: new Abstract: Tabular foundation models based on in-context learning have recently emerged as strong alternatives to task-specific model fitting. However, the current
Anissa Gardizy / Wall Street Journal: Sources: Anthropic has signed a $35B cloud deal with Nvidia-backed Lambda; Nvidia will hold the lease on and supply chips to a Texas data center built by Hut 8 —
The Information: Sources: OpenAI starts letting some major customers pay only when its AI completes tasks, as Salesforce and other AI providers test outcome-based pricing — OpenAI in recent months has
arXiv:2608.28270v1 Announce Type: new Abstract: We present a real-time semantic navigation framework for Unmanned Aerial Vehicles (UAVs) focused on improving time efficiency in the Object Goal Navigat
arXiv:2608.28242v1 Announce Type: new Abstract: Unobtrusive ballistocardiographic (BCG) sensing is a promising modality for long-term sleep-apnea monitoring, yet it remains unclear which signal featur
arXiv:2606.20419v2 Announce Type: replace Abstract: Vision-language models (VLMs) often generate fluent but visually unsupported descriptions, especially by mentioning objects absent from the image. W
arXiv:2608.28099v1 Announce Type: cross Abstract: Real-time classification during language model inference is valuable for safety filtering, behavioral analysis, and model monitoring, but current appr
arXiv:2606.20543v2 Announce Type: replace Abstract: Autoregressive image models treat images as 1D token sequences, inheriting the next-token factorization of language models. This flattening discards
arXiv:2608.28090v1 Announce Type: new Abstract: Humanoid robots with quasi-direct-drive actuators continuously generate joint torque while standing, whereas seated humans delegate weight support to ch
arXiv:2608.28229v1 Announce Type: cross Abstract: Grammar-constrained decoding helps large language models produce syntactically valid structured outputs, such as code, JSON, and SQL. For context-free
arXiv:2509.19212v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) are increasingly deployed in real-world applications, yet their ability to make context-aware safety decisi
arXiv:2608.28279v1 Announce Type: new Abstract: Multimodal lifelong navigation requires an agent to autonomously explore unseen environments while sequentially completing navigation tasks specified by
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:2608.27881v1 Announce Type: new Abstract: Recently, many streaming video understanding methods have been proposed by constructing an external memory to store historical data for computational re
arXiv:2607.15058v2 Announce Type: replace Abstract: CAD-to-image alignment aims to estimate an object's 9D pose (rotation, translation, and anisotropic scale) from a single RGB image, with application
arXiv:2608.27783v1 Announce Type: cross Abstract: Speech LLMs are usually graded after they answer, although an operating system first has to decide whether a waveform should be sent to the model. We
arXiv:2608.28408v1 Announce Type: new Abstract: Tabular data, as a core data format in machine learning, often lacks the discriminative power needed for high-performance modeling due to insufficient f
arXiv:2608.28248v1 Announce Type: cross Abstract: The ability of Large Vision Language Models (LVLMs) to read text within document images is crucial, as it enables various applications such as Documen
arXiv:2608.27843v1 Announce Type: new Abstract: Contemporary language models can converse fluently and influence human decisions, yet their exchanges do not enter a continuing, vulnerable life of thei
arXiv:2608.27911v1 Announce Type: new Abstract: Agents with smaller language-model backbones are less expensive but can drift into persistent failure modes, whereas those with larger backbones are gen
arXiv:2509.24192v2 Announce Type: replace Abstract: Vision-language models (VLMs) have advanced multimodal perception, demonstrated by open-vocabulary object detection with simple language queries. St
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
arXiv:2608.27948v1 Announce Type: new Abstract: Test-time adaptation (TTA) on graphs aims to adapt a graph neural network (GNN) that is well-trained on the training graph to the test graph, which invo
arXiv:2608.27871v1 Announce Type: new Abstract: Long-video understanding remains challenging for Multimodal Large Language Models (MLLMs) due to limited context length. Uniform sampling may miss cruci
arXiv:2608.27612v1 Announce Type: cross Abstract: In neuroevolution, indirect encoding generates neural network connectivity from a compact genome rather than specifying each connection. ES-HyperNEAT
arXiv:2608.28170v1 Announce Type: new Abstract: Purpose - This study investigates the feasibility of restoring missing text caused by physical lacunae in damaged ancient manuscripts using language mod
arXiv:2608.28524v1 Announce Type: new Abstract: Texture image classification plays a significant role in computer vision applications, including industrial inspection, medical image analysis, remote s
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:2608.28150v1 Announce Type: new Abstract: Which geometry controls the rank complexity of normalized softmax attention? We study maximum-row-ell_1 approximation rank, exactly the least unrestrict
arXiv:2603.19423v3 Announce Type: replace-cross Abstract: Large language model (LLM) agents increasingly rely on external tools (file operations, API calls, database transactions) to autonomously comp
arXiv:2608.27750v1 Announce Type: cross Abstract: The hidden states of large language models (LLMs) are known to capture rich information relating to model knowledge and behavior that can be hard to e
A hallucinated event, Crono awakens in his modest bedroom of 2095... I am using local models since 2025 January. My daily driver is qwen 3.6 35B A3B, which works pretty well for coding tasks, but I al
arXiv:2606.17399v2 Announce Type: replace Abstract: When small transformers grok modular multiplication, prior work reports that the learned embedding has a 'dense' Fourier spectrum requiring all freq
arXiv:2608.27465v1 Announce Type: new Abstract: As large language models (LLMs) are increasingly used for everyday decision-making advice, whether a model shifts the direction of its advice according
The First Golden Age of AI writing is now over. For a brief period of time, many people were better off having Claude do a lot of their writing, because it is a pretty good writer & AI detectors were
Ethan Mollick / One Useful Thing: The Hugging Face and Mythos 5 incidents show AI agents can self-organize, raising questions about how much agency they should have and when to seek human input — From
The independent review of the OpenAI Hugging Face incident, supposedly a watershed moment in cybersecurity, wasn't done by a cybersecurity firm and the authors have no cybersecurity experience. That's
arXiv:2512.12066v3 Announce Type: replace-cross Abstract: Current safety evaluations of large language models rely on single-shot testing, implicitly assuming that model responses are deterministic an
Kirsten Korosec / TechCrunch: The Pentagon launches ChatGPT Mil and Grok for Government on its GenAI.mil platform, giving its 3M personnel access to AI tools “tailored to warfighter needs” — The Penta
arXiv:2511.16695v2 Announce Type: replace Abstract: Art is a deeply personal and expressive medium, where each artist brings their own style, technique, and cultural background into their work. Tradit
arXiv:2509.04438v3 Announce Type: replace-cross Abstract: Unified models (UMs) combine visual understanding (I2T) and generation (T2I) in a single framework. We focus on T2I and I2T, where cross-consi
arXiv:2608.27885v1 Announce Type: new Abstract: Multimodality translation (e.g., text-to-image) is a core generative AI task. However, existing approaches (1) follow generative paths that do not direc
This is a watershed moment for cybersecurity, but the implications go much further than that. When agents go out into the world and are put in users’ hands, they will be tasked with actions that requi
This WikiSkill paper from Google is a must-read. At a high level, it shows the effectiveness of persistent agents, knowledge bases, and skills. @karpathy popularized LLM Wikis. But this paper provides
arXiv:2608.27888v1 Announce Type: new Abstract: Neural texture compression (NTC) achieves higher compression ratios than BCn formats but suffers from GPU thread divergence, which significantly reduces
arXiv:2608.27931v1 Announce Type: new Abstract: This study proposes a novel framework to estimate parameters for reproducing target multicellular patterns using an agent-based model (ABM). Two major c
arXiv:2608.28393v1 Announce Type: cross Abstract: Repurchase recommenders in e-commerce are commonly framed as a binary question asking 'will this customer buy this item within W days', a formulation
Today, Transluce is releasing the most expansive independent evaluation to date of how AI systems respond to users experiencing mental health crises. We evaluated 77 model variants from OpenAI, Anthro
Today, we also open the door to Fireworks Lab: Embed forward-deployed researchers and engineers to co-design or build your model for you. Join leaders like @cursor_ai, @harvey, @figma, @vercel, @cogni
arXiv:2608.28138v1 Announce Type: new Abstract: Adapting video vision-language models (VLMs) is computationally expensive because video inputs produce a large number of visual tokens, making both fine
arXiv:2606.17016v2 Announce Type: replace Abstract: As LLM agents are deployed in long-horizon sessions, context accumulation drives up inference costs. Existing approaches utilize text pruning or dyn
arXiv:2606.12451v2 Announce Type: replace-cross Abstract: Large language models deployed as agents over large tool catalogs face a critical tool-retrieval bottleneck. As embedding-based retrieval appr
arXiv:2608.27540v1 Announce Type: cross Abstract: We develop a mathematical theory of superposition in neural networks using tools from frame theory and compressed sensing. In our model, a sparse bina
arXiv:2608.27578v1 Announce Type: cross Abstract: Training effective foundation models requires massive and organized datasets, yet scientific domains such as nuclear fusion present unique challenges