Knowledge catalogue
arXiv:2609.25108v1 Announce Type: new Abstract: Visual data is increasingly consumed by machine-vision systems rather than by human observers. Image Coding for Machines (ICM) compresses images assumin
Matthias Bastian / The Decoder: Anthropic says Opus 5.5 matches Fable 5.1 “on most tasks” while costing about 40% less to run than Opus 5; Opus 5.5 costs 4/1M input and 20/1M output tokens — Ask about
arXiv:2609.24417v1 Announce Type: new Abstract: Despite advances in long-context inference, large language models (LLMs) remain fundamentally limited by the key-value (KV) caching mechanisms that are
arXiv:2609.24099v1 Announce Type: new Abstract: Body-cue recognition can support assistive robots, but benchmark accuracy does not guarantee reliable behavior under a robot-camera viewpoint. We presen
arXiv:2411.10163v3 Announce Type: replace Abstract: Large language models (LLMs) demonstrate remarkable performance across various tasks, prompting researchers to develop diverse evaluation benchmarks
arXiv:2609.22278v1 Announce Type: new Abstract: Quadruped manipulators enable mobile grasping in complex environments, yet their whole-body control policies remain vulnerable to unreliable onboard vis
arXiv:2609.24359v1 Announce Type: new Abstract: Image forensics is increasingly an open-world problem: manipulations range from fully synthetic images to localized edits, splicing and swapping, while
arXiv:2512.02851v5 Announce Type: replace Abstract: Visual traversability estimation is central to autonomous navigation, yet most approaches either rely on prompt-driven Vision-Language Model (VLM) o
arXiv:2510.26915v2 Announce Type: replace Abstract: While heterogeneous teams have typically been designed for well-specified missions with known semantics, generative intelligence, i.e., large langua
arXiv:2609.24172v1 Announce Type: new Abstract: Legends are fundamental to chart understanding, as reliable interpretation requires correctly binding legend entries to corresponding visual marks. Whil
arXiv:2609.24742v1 Announce Type: new Abstract: Humanoid robots are increasingly being popular and developed for human-centered applications, yet their ability to provide intelligent conversations and
arXiv:2609.23371v1 Announce Type: new Abstract: Long-context language models interface with external knowledge through raw natural language. In retrieval-augmented systems, this creates a persistent i
arXiv:2609.23336v1 Announce Type: new Abstract: Localizing and describing fine-grained differences between near-identical images is a critical yet underexplored capability for multimodal large languag
arXiv:2609.24812v1 Announce Type: new Abstract: Voice provides a natural and immediate interface for AI agents. Many settings in which voice agents could be useful, including meetings, households, and
Must-read papers of the week ▪️ JEPA-Anything ▪️ Modality-Autoregressive World-Action Models ▪️ In-Context Robot Learning with VLM Agents ▪️ Dream-RSI: Recursive Self-Improvement through Evolving Worl
arXiv:2609.23495v1 Announce Type: new Abstract: Failures of high-resolution MLLMs are commonly attributed to a visual problem, motivating zooming, cropping, and related visual interventions to recover
They just merged it https://github.com/Comfy-Org/ComfyUI/pull/16442 TL;DR: it's a prompt enhancer that you can use to improve Qwen Image 2.1 prompt Usage: Download these qwen3.5_9b_qwen_image , t2i fo
Recommended if you work on agent memory. Retrieval is the hardest memory problem in most harnesses because agents keep pulling stale context. AML tests this with a coding track of 150 software tasks,
arXiv:2609.22213v1 Announce Type: new Abstract: Temporal Knowledge Graph Question Answering (TKGQA) requires answer inference from evidence that is both structurally valid and temporally admissible. E
arXiv:2609.22234v1 Announce Type: new Abstract: Instruction hierarchy (IH) alignment teaches language models to prioritize higher-level instructions when inputs conflict. While studied primarily in te
arXiv:2609.23716v1 Announce Type: new Abstract: Textual-gradient methods automate prompt optimization through natural-language feedback, but their iterative updates can be unstable. We identify two so
arXiv:2609.22943v1 Announce Type: new Abstract: Efficient large language model (LLM) instruction tuning requires selecting response supervision with supporting prompt context. Existing methods typical
arXiv:2609.22463v1 Announce Type: new Abstract: Sleep monitoring using wearable data has shown promise for personal health, yet large language model (LLM)-based summarization and question answering re
arXiv:2609.23939v1 Announce Type: new Abstract: Effective communication between users and AI agents is essential for human-AI collaboration. The XY problem is a well-known communication pitfall where
arXiv:2609.21386v1 Announce Type: cross Abstract: Comprehensive video understanding is crucial for advancing artificial intelligence toward the intricate dynamics of the physical world. While recent a
arXiv:2609.20974v1 Announce Type: new Abstract: In Mixture-of-Experts language models, the router typically selects and weights experts based on the token's hidden state, utilizing limited contextual
arXiv:2601.07316v2 Announce Type: replace-cross Abstract: Automated electrocardiogram diagnosis using deep learning remains limited by signal-agnostic representations that treat multi-lead recordings
arXiv:2609.20888v1 Announce Type: new Abstract: Massive KV caches can cause severe memory-bandwidth bottlenecks during long-context decoding. Sparse attention methods mitigate this via selective loadi
arXiv:2609.21293v1 Announce Type: new Abstract: Autonomous software generation (ASG) aims to turn human requirements into executable applications, but delivering these applications does not necessaril
arXiv:2602.13699v2 Announce Type: replace Abstract: Large language models (LLMs) often generate plausible yet incorrect answers, posing risks in safety-critical settings such as medicine. Human evalua
lots of them! Reality is that LLM APIs are far from being the best way to do AI for 90% of use cases in the real world (they're too overkill, slow, expensive, hard to control,...). We will discover th
arXiv:2609.20850v1 Announce Type: new Abstract: While Multimodal Large Language Models (MLLMs) show remarkable advancements, their cross-modal capabilities introduce complex vulnerabilities that easil
arXiv:2609.21369v1 Announce Type: cross Abstract: This paper presents a comprehensive framework for robot manipulation failure analysis that includes binary failure detection, failure categorization,
arXiv:2609.21859v1 Announce Type: new Abstract: Nearly 90% of drugs entering clinical development ultimately fail, despite billions of dollars in investment. Pharmaceutical companies therefore rely on
RTX 5090 random black screen + 100% fans + hard lock; sometimes no POST until AC power is removed — gaming, ComfyUI and Ollama I am looking for help diagnosing a very intermittent but increasingly fre
In February OpenAI stopped reporting SWE-bench Verified and recommended other labs stop too. Every frontier model they tested could reproduce the human-written reference fix, or verbatim details of th
I needed a relatively simple but acceptable level of AI for working on one project. I didn't have any heavy requests, I just needed to give the AI access to the project files so it could search throug
Hello, I know some of us may be tempted to rent out our expensive GPUs to recoup some of the cost of self-hosting, and it should be obvious that this can be a risky decision. I decided to try hosting
Inference scaling part 1. Starting with a modded text generation function (temperature scaling, top-p filtering, multinomial sampling) to generate diverse outputs for self-consistency and best-of-N (i
🚨 OBAMA ON AI: 'If we are thinking about AI just in terms of how do we cure cancer or get better energy, you can do that without having agentic AI and having it just roaming free in the internet. The
Oh My Pi + vLLM on two 3090s. Average wait per turn went from 28s to 7s, mostly from changing omp settings: explicit effort level on every role (unset ones defaulted to xhigh) thinking_token_budget of
arXiv:2609.19555v1 Announce Type: cross Abstract: Artificial intelligence for plant disease analysis has advanced from task-specific classifiers to multi-modal models capable of jointly interpreting v
arXiv:2603.02540v2 Announce Type: replace Abstract: Large language models (LLMs) display a unified 'general factor' of capability across 10 benchmarks (a finding confirmed by our factor analysis of 15
arXiv:2609.20620v1 Announce Type: cross Abstract: Autonomous underwater vehicles (AUVs) operating beyond reliable communications must recover from failures without human intervention. We investigate a
arXiv:2609.19606v1 Announce Type: new Abstract: This empirical study is an independent reproduction of the dissociation Zhao reported in 2026. The shape of a large language model's chain-of-thought en
even the anti-woke media sure loves this narrative. doesn’t make it true. 'I worked at OpenAI for two years before resigning in 2024. Fears that AI will cause human extinction are real. You should tak
arXiv:2609.19569v1 Announce Type: cross Abstract: Disease severity classification for genetic conditions is subjective and labor-intensive, creating bottlenecks in genomic screening, where commercial
arXiv:2609.19961v1 Announce Type: new Abstract: Networked low-altitude unmanned aerial vehicles (UAVs) need reliable and adaptive decision-making capabilities to operate under uncertain observations,
arXiv:2609.20323v1 Announce Type: new Abstract: Three-dimensional reconstruction from unorganized point clouds remains a challenging problem in computer vision, geometric modeling, and computer-aided
arXiv:2609.20319v1 Announce Type: cross Abstract: Grover search, amplitude amplification, and quantum counting all rely on the same reusable subroutine, a phase oracle, whose construction the algorith
Hey community, Jovan from UkisAI here, We're the team behind Swift Qwen3.8 27B, the Qwen model with token usage and overthinking error improvements Our estimate is that we can make a great improvement
arXiv:2609.19610v1 Announce Type: new Abstract: Understanding humans over long horizons requires agents to infer not only what people need in the moment, but also how routines form, why they repeat, a
arXiv:2609.20612v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) lets a language model learn from a frozen copy of itself that sees an answer or a worked solution. Giving the teacher
arXiv:2609.20261v1 Announce Type: new Abstract: Autonomous agents derive concrete mutations from database reads, retrieved evidence, policy, beliefs, and delegated authority. Those inputs may change w
arXiv:2609.18520v1 Announce Type: new Abstract: Collective intelligence is a collaborative autonomy paradigm in which multiple agents pursue shared objectives through local perception, information exc
arXiv:2609.18516v1 Announce Type: new Abstract: While Large Language Models excel in natural language processing, efficiently extending their capabilities to spoken input remains a significant challen
arXiv:2609.17923v1 Announce Type: new Abstract: Sports highlight detection aims to identify the most exciting and meaningful moments from long sports videos. While existing methods often emphasize vis
arXiv:2609.19128v1 Announce Type: new Abstract: Language agents remain brittle in interactive environments, where success requires long-horizon state tracking, valid action execution, and recovery fro
arXiv:2609.17786v1 Announce Type: new Abstract: Fairness-aware model compression requires selecting methods and configurations that balance accuracy, fairness, and deployment cost. These decisions bec
arXiv:2609.17538v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for structured information extraction from documents, yet their behavior under realistic OCR noise re