IR3DE: A Linear Router for Large Language Models
arXiv:2606.06098v1 Announce Type: new Abstract: Foundational Large Language Models (LLMs) demonstrate proficiency on a wide range of general tasks, and achieve remarkable results on various specialize
Knowledge catalogue
arXiv:2606.06098v1 Announce Type: new Abstract: Foundational Large Language Models (LLMs) demonstrate proficiency on a wide range of general tasks, and achieve remarkable results on various specialize
arXiv:2507.06219v2 Announce Type: replace Abstract: Data scaling has driven remarkable success in foundation models for Natural Language Processing (NLP) and Computer Vision (CV), yet the principles o
arXiv:2606.05172v1 Announce Type: cross Abstract: Diffusion-based image editing has achieved strong visual fidelity under natural language instructions, yet most existing systems still operate at the
Isomorphic likely that every single person in that game was already familiar with this Levels of Mafia/Werewolf/Secret Hitler: • You play, poorly • You play, skillfully • You play, poorly, so that peo
Yoshua Bengio appeared as a guest on 'The Most Interesting Thing in AI' podcast hosted by N.X. Thompson, where he discussed various topics related to artificial intelligence. The appearance was shared
It's the time of the year when you shouldn't come to New York if you are not planning on moving permanently. It's the time of the year when you shouldn't come to New York if you are not planning on mo
This is a social media post from ComfyUI's X (Twitter) account inviting users to join their community or platform. Without access to the specific post content, it likely promotes ComfyUI's node-based
Join us on a live interview with the CEO of ComfyUI! Today on TWiST, we're joined by @yoland_yan, Founder/ CEO of @ComfyUI. With 4M users, 150K downloads a day, and a $500M valuation from Craft, @Comf
⚠️ Keep your eye on the ball, and don’t panic over Anthropic’s new blog. Here’s why: Anthropic is trying to strike terror into everyone’s hearts – “full recursive self-improvement also might increase
arXiv:2606.06078v1 Announce Type: new Abstract: Autoregressive (AR) image generation models are highly expressive but computationally intensive, motivating effective model compression. Knowledge disti
arXiv:2606.05624v1 Announce Type: new Abstract: Text-conditioned 3D human motion models now synthesize plausible motions from prompts, but practical animation and embodied-agent workflows rarely stop
arXiv:2606.06049v1 Announce Type: new Abstract: Intra-vehicular robots in spacecraft help reduce astronaut workload and improve mission efficiency. Recent research focuses on using deep learning metho
arXiv:2606.05873v1 Announce Type: cross Abstract: Humanoid robots hold great promise for operating in human-centered environments, yet ladder climbing remains one of the most challenging tasks due to
arXiv:2606.05182v1 Announce Type: new Abstract: Large language models discard critical details when conversation history is compacted to fit within finite context windows. We present LANTERN (Layered
arXiv:2606.05937v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly used, including in political applications, but their political fairness has been little studied. We assess
Last night, I read the entirety of C.S. Lewis' The Screwtape Letters. It's a novel told in the form of letters written by a demon to another demon instructing him on ways to manipulate his 'patient' t
Last year: people had to steal GPU’s from armored trucks. This year: SpaceX is leasing to GPUs left, right, and center, because Xai couldn’t figure out what to do with them. SpaceX just disclosed a ne
arXiv:2512.21218v2 Announce Type: replace Abstract: While Large Multimodal Models (LMMs) have made significant progress, they remain largely text-centric, relying on language as their core reasoning m
arXiv:2606.06447v1 Announce Type: new Abstract: Large language models often improve reasoning by generating explicit chain-of-thought (CoT), demonstrating the importance of intermediate computation. H
arXiv:2606.06087v1 Announce Type: new Abstract: Agent systems increasingly use textual skills to encode reusable task procedures, but injecting these skills into the prompt at every step incurs substa
arXiv:2606.05400v1 Announce Type: cross Abstract: Long-horizon autoformalization of research mathematics fails not only at hard lemmas, but at scale: statements drift, dependencies tangle, context dec
arXiv:2606.05501v1 Announce Type: new Abstract: The estimation of odometry in legged robots depends on the assumption that the velocity of the foot with respect to the world remains zero during the st
arXiv:2606.05422v1 Announce Type: new Abstract: Learning from demonstratins (LfD) is usually performed over Euclidean spaces, while the robot state, e.g. orientation, naturally evolves over curved spa
arXiv:2606.05833v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) excel at 2D semantic understanding but lack intrinsic 3D awareness, resulting in representations that fail to m
arXiv:2606.05952v1 Announce Type: new Abstract: In this work, we propose an agentic gamification framework for hazard-informed learning of robot safety policies through synthetic scenarios. We model s
arXiv:2503.23300v2 Announce Type: replace Abstract: Understanding and predicting human visuomotor coordination is crucial for applications in robotics, human-computer interaction, and assistive techno
arXiv:2602.08503v2 Announce Type: replace-cross Abstract: Self-correction is essential for solving complex reasoning problems in vision-language models (VLMs). However, existing reinforcement learning
arXiv:2606.06178v1 Announce Type: cross Abstract: Large language models (LLMs) present a trade-off between performance and cost, where more powerful models incur greater expense. LLM routing aims to m
arXiv:2606.06076v1 Announce Type: cross Abstract: While vision-language models excel at general multimodal understanding, they still struggle with visual spatial planning. We attribute this to a perce
arXiv:2606.06320v1 Announce Type: cross Abstract: Machine unlearning aims to remove targeted knowledge from a trained model while preserving its general capabilities. For autoregressive language model
arXiv:2606.05538v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models achieve strong performance through conditional computation, but their large parameter footprint poses deployment chall
arXiv:2606.05737v1 Announce Type: new Abstract: Diffusion-based vision-language-action (VLA) models often inherit the image-generation view: actions are generated by iterative denoising. We argue that
Let’s go 🚀 Building AI that Builds AI: Introducing the Sakana AI RSI Lab 🚀 https://sakana.ai/rsi-lab Today, we are announcing the Sakana AI Recursive Self-Improvement (RSI) Lab: a dedicated research g
arXiv:2508.20693v2 Announce Type: replace-cross Abstract: Ontologies and taxonomies of research fields are critical for managing and organising scientific knowledge, as they facilitate efficient class
arXiv:2606.05774v1 Announce Type: new Abstract: Dense 3D reconstruction has demonstrated immense potential for spatial understanding, yet its viability as a real-time, onboard representation for auton
Lightricks is laying off 75 employees (17% of workforce) as it continues restructuring amid AI disruption, less than six months after a previous round of 85 layoffs. The company is splitting into two
arXiv:2606.05354v1 Announce Type: new Abstract: Retinal blood vessel segmentation plays a vital role in the early detection of diabetic retinopathy and glaucoma. While recent deep learning models have
Gary Marcus argues for a specific rationale supporting a potential OpenAI bailout, though the exact reasoning is not detailed in the available information. Given Marcus's background as an AI researche
arXiv:2606.06048v1 Announce Type: new Abstract: Pathological gait datasets remain scarce due to privacy, recruitment, cost, and movement variability. Our work presents a multimodal LLM-guided framewor
arXiv:2502.14145v3 Announce Type: replace Abstract: Achieving full-duplex communication in spoken dialogue systems (SDS) requires real-time coordination between listening, speaking, and thinking. This
arXiv:2606.05489v1 Announce Type: new Abstract: Retrieval systems underpin modern AI applications -- spanning visual search, recommendation engines, and multi-modal question answering. Modern multi-st
arXiv:2606.06286v1 Announce Type: new Abstract: Large language models can reproduce training data, but existing memorization evaluations mostly measure whether models can be forced to do so, rather th
LLMs do not teach people to think critically. Colleges do. Hot take: Universities charge $300,000 for a degree that teaches you skills any LLM can do for free. At some point we need to have an honest
arXiv:2606.05486v1 Announce Type: new Abstract: Prompt ambiguity is a common source of failure in large language models, but is difficult to localize because it is a latent property of the prompt, whi
arXiv:2606.05677v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have advanced image and video understanding and can increasingly handle longer visual inputs. Long-horizon ta
arXiv:2606.06042v1 Announce Type: new Abstract: Developing unified video generation and editing models capable of interpreting interleaved multimodal inputs is a promising yet challenging frontier fie
arXiv:2606.05315v1 Announce Type: new Abstract: Implicit chain-of-thought (iCoT) methods aim to internalize reasoning in large language models, but often underperform explicit CoT prompting. We empiri
Love this. Juan Hernandez immigrates to the US, learns how to weld because it pays well, begins contracting at SpaceX, gets full time role + $10,000 equity. It’s now worth just under a million dollars
Luca (@agi2asi) built Grid to centralize 12 different Google Drives into one hub. With Replit, he turned a prompt into an AI-powered employee hub in just 10 minutes. Now, team members can ask about an
Luca built Grid to centralize 12 different Google Drives into one hub. With Replit, he turned a prompt into an AI-powered employee hub in just 10 minutes. Now, team members can ask about anything from
arXiv:2606.06267v1 Announce Type: new Abstract: Circuit discovery methods identify subgraphs that explain specific model behaviors, and structural differences between discovered circuits are commonly
arXiv:2606.05749v1 Announce Type: new Abstract: Iterative retrieval-reasoning agents have recently shown promise for multimodal long-document question answering. However, most existing systems maintai
Kif Leswing / CNBC: Marvell and Flex, a contract manufacturer for electronics, will join the S&P 500; MRVL jumps 6%+ after hours after closing down 16.74% amid a broader sell-off — - Marvell Technolog
arXiv:2606.05494v1 Announce Type: new Abstract: Automatic text summarization has become increasingly important due to the rapid growth of digital textual information. This paper presents a Multi-Model
Jeremy Howard discusses a significant increase in output capabilities driven by agentic AI systems, while noting that adoption rates remain completely flat across the board. The observation suggests a
arXiv:2603.07294v2 Announce Type: replace Abstract: Fine-grained understanding and species-specific multimodal question answering are vital for advancing biodiversity conservation and ecological monit
arXiv:2606.05177v1 Announce Type: new Abstract: Existing multimodal safety benchmarks focus solely on visual inputs and cannot assess Omni Large Language Models (LLMs) that process vision, audio, and
arXiv:2606.06058v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards is ideal for multi-constraint instruction following, yet standard group-relative policy optimization (G
arXiv:2606.05970v1 Announce Type: new Abstract: Large language models are increasingly used for structured extraction from clinical free-text notes, but the sensitivity of their output to upstream con
arXiv:2606.05843v1 Announce Type: new Abstract: While Multimodal Large Language Models (MLLMs) demonstrate remarkable proficiency on complex vision-language tasks, the mechanisms by which they extract