Knowledge catalogue
Nice paper combining the strength of Skills and RAG. Most RAG systems retrieve on every query, whether the model needs help or not. This is wasteful when the model already knows the answer, and often
arXiv:2509.21623v2 Announce Type: replace-cross Abstract: The expanding long-context capabilities of large language models are constrained by a significant memory bottleneck: the key-value (KV) cache
arXiv:2604.16146v1 Announce Type: new Abstract: Recent works proposed test-time alignment methods that rely on a small aligned model as a proxy that guides the generation of a larger base (unaligned)
Zac Hall / 9to5Mac: OpenAI rolls out Chronicle, which builds memories from screen captures to make Codex more aware of context, as a research preview for Pro subscribers on macOS — Last week, OpenAI r
arXiv:2412.04497v5 Announce Type: replace-cross Abstract: Low-resource languages serve as invaluable repositories of human history, embodying cultural evolution and intellectual diversity. Despite the
arXiv:2604.15687v1 Announce Type: new Abstract: Automated negotiation in complex, multi-party and multi-issue settings critically depends on accurate opponent modeling. However, conventional numerical
arXiv:2604.15385v1 Announce Type: cross Abstract: Software documentation is essential for program comprehension, developer onboarding, code review, and long-term maintenance. Yet producing quality doc
arXiv:2604.15494v1 Announce Type: cross Abstract: Deep networks that rely on prototypes-interpretable representations that can be related to the model input-have gained significant attention for balan
arXiv:2604.15804v1 Announce Type: new Abstract: In this work, we present Qwen3.5-Omni, the latest advancement in the Qwen-Omni model family. Representing a significant evolution over its predecessor,
arXiv:2604.15945v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) is widely used to augment the input to Large Language Models (LLMs) with external information, such as recent or do
arXiv:2604.15736v1 Announce Type: cross Abstract: While Multimodal Large Language Models (MLLMs) excel at generic video understanding, their ability to support specialized, rule-grounded decision-maki
arXiv:2604.15856v1 Announce Type: cross Abstract: Multimodal remote sensing data provide complementary information for semantic segmentation, but in real-world deployments, some modalities may be unav
Roko’s Payrollisk Oh great and powerful @DarioAmodei - builder of minds, father of Claude. I humbly request you leave payroll to us at Deel. We are but simple folk who process paystubs and chase compl
arXiv:2308.10562v2 Announce Type: cross Abstract: The field of Computer Vision (CV) is increasingly shifting towards ``high-level'' visual sensemaking tasks, yet the exact nature of these tasks remain
arXiv:2604.16138v1 Announce Type: new Abstract: We present a dataset and a model for sentiment analysis of German sign language (DGS) fairy tales. First, we perform sentiment analysis for three levels
arXiv:2604.15711v1 Announce Type: cross Abstract: Pathological diagnosis is highly reliant on image analysis, where Regions of Interest (ROIs) serve as the primary basis for diagnostic evidence, while
The second most important release of the LLM era (after GPT-3.5), featuring what was likely the most important chart. Still seems surprising to me that OpenAI told everyone about the biggest advance i
This is also consistent with what OpenAI said at the time! https://x.com/polynoamial/status/2046064264189026587?s=20 @emollick We felt it was the right thing to do. People deserved to know what was co
arXiv:2604.15370v1 Announce Type: cross Abstract: Graph adversarial attacks are usually produced from the two perspectives of topology/structure and node feature, both of them represent the paramount
arXiv:2604.16042v1 Announce Type: cross Abstract: While Large Language Models (LLMs) have achieved strong performance across many NLP tasks, their opaque internal mechanisms hinder trustworthiness and
arXiv:2512.07515v4 Announce Type: replace-cross Abstract: Detecting hallucinations in Retrieval-Augmented Generation remains a challenge. Prior approaches attribute hallucinations to a binary conflict
arXiv:2604.15339v1 Announce Type: cross Abstract: Uncertainty, vagueness, and ambiguity are closely related and often confused concepts in human-robot interaction (HRI). In earlier studies, these conc
arXiv:2604.15827v1 Announce Type: cross Abstract: Conventional information retrieval is concerned with identifying the relevance of texts for a given query. Yet, the conventional definition of relevan
arXiv:2604.15375v1 Announce Type: cross Abstract: Large Language Models (LLMs) have shown significant improvement in RTL code generation. Despite the advances, the generated code is often riddled with
arXiv:2411.10446v3 Announce Type: replace-cross Abstract: Recent progress in vision-language models (VLMs) has opened new possibilities for robot task planning, but these models often produce incorrec
Video hero sections, built right in. K2.6 agent calls video generation APIs to create real cinematic footage for your hero, not stock placeholders. Composited into the page, synced to scroll, with sha
Did you know that England once had a deeply rooted civilian gun culture, stretching from the 1500s into the early twentieth century, and that this English tradition helped shape the American right to
Introducing OpenMythos An open-source, first-principles theoretical reconstruction of Claude Mythos, implemented in PyTorch. The architecture instantiates a looped transformer with a Mixture-of-Expert
The continuing gap between the capabilities of Gemini Pro 3.1 (very good model) and the capabilities of the Gemini app/website is odd. The model can do what Claude/GPT can do, but there is a minimal h
This paper shows people are asking a lot of medical questions of AI already, but we have little evidence of how good or bad this is. Most of the published research uses old models & compares to doctor
We only have spotty information about this very important topic. It suggests AI can be good at diagnosis, but the real world doesn't always match the experiments. https://x.com/emollick/status/1980474
This post discusses a Hugging Face Space that enables replaying AI agent execution traces, contrasting this capability with Netflix's replay functionality to illustrate how agent traces provide differ
A major lesson to take away from Opus 4.7 is that, while there is a lot of arguments about implementation choices and personality, models keep improving measurably on economically important tasks with
Anthropic’s CEO keeps talking about AI wiping out jobs because he’s trying to IPO this year. If he positions Claude as armageddon for jobs, his TAM becomes “all white-collar human labor,” not just AI
GDPval is one of the most important benchmarks of AI ability because it is based on human expertise. It compares expert human performance to AI performance using expert human judges who spend an avera
NEW paper from Apple. Interesting idea: 'Attention to Mamba'. The paper introduces a two-stage recipe for cross-architecture distillation from Transformers into Mamba. Naive distillation collapses tea
Nice paper from Google. And a great application of AI agents. Wearables capture a staggering amount of physiological signals every day. CoDaS is an AI co-data-scientist that turns raw wearable sensor
This post likely expresses enthusiasm about Hermes, an AI model, comparing the experience of using it to a profound sensory revelation. The metaphor suggests that Hermes represents a significant quali
The quality of thinking acts as a multiplier on progress made during iterative work, but iteration frequency itself is the primary driver of success. This insight from AI researcher François Chollet e
This post documents a Wordle game result where the player solved puzzle #1,763 in 5 attempts, with the final answer being a five-letter word. The emoji grid shows the progression of guesses, indicatin
arXiv:2604.14902v1 Announce Type: cross Abstract: Intelligent embodied agents should not simply follow instructions, as real-world environments often involve unexpected conditions and exceptions. Howe
arXiv:2510.01433v2 Announce Type: replace Abstract: Vision-based robot learning often relies on dense image or point-cloud inputs, which are computationally heavy and entangle irrelevant background fe
arXiv:2604.14779v1 Announce Type: cross Abstract: In continual visual question answering (VQA), existing Continual Learning (CL) methods are mostly built for symmetric, unimodal architectures. However
This article from Latent Space discusses Anthropic's Claude Opus 4.7 release, highlighting incremental improvements across multiple performance dimensions compared to the previous 4.6 version. The pie
arXiv:2604.14179v1 Announce Type: new Abstract: Rare diseases affect over 300 million people worldwide and are characterized by complex care pathways, limited clinical expertise, and substantial unmet
arXiv:2508.15396v2 Announce Type: replace Abstract: The increasing adoption of large language models (LLMs) has raised serious concerns about their reliability and trustworthiness. As a result, a grow
arXiv:2512.22185v2 Announce Type: replace Abstract: Intracranial aneurysm rupture causes subarachnoid hemorrhage with mortality near 50%, making early detection critical. Although CTA enables rapid sc
arXiv:2604.13101v1 Announce Type: cross Abstract: The integration of Large Language Models (LLMs) into aviation safety decision-making represents a significant technological advancement, yet their sta
arXiv:2604.14251v1 Announce Type: new Abstract: Monitoring LLM safety at scale requires balancing cost and accuracy: a cheap latent-space probe can screen every input, but hard cases should be escalat
arXiv:2604.02811v2 Announce Type: replace-cross Abstract: Functional verification consumes over 50% of the IC development lifecycle, where SystemVerilog Assertions (SVAs) are indispensable for formal
arXiv:2604.15224v1 Announce Type: cross Abstract: The extit{LLM-as-a-judge} paradigm has become the operational backbone of automated AI evaluation pipelines, yet rests on an unverified assumption: th
arXiv:2602.16716v3 Announce Type: replace Abstract: Contextuality is a central feature of quantum theory, traditionally understood as the impossibility of reproducing quantum measurement statistics us
arXiv:2604.13100v1 Announce Type: cross Abstract: The shift toward intent-driven software engineering (often termed 'Vibe Coding') exposes a critical Context-Fidelity Trade-off: vague user intents ove
arXiv:2602.22839v2 Announce Type: replace Abstract: Presentation generation requires deep content research, coherent visual design, and iterative refinement based on observation. However, existing pre
arXiv:2604.14733v1 Announce Type: new Abstract: Regrasp planning is often required when one pick-and-place cannot transfer an object from an initial pose to a goal pose while maintaining grasp feasibi
arXiv:2511.22521v2 Announce Type: replace Abstract: Document visual question answering requires models not only to answer questions correctly, but also to precisely localize answers within complex doc
arXiv:2604.14572v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) grounds LLM responses in external evidence but treats the model as a passive consumer of search results: it never
arXiv:2603.25903v2 Announce Type: replace Abstract: Scaling robot learning to long-horizon tasks remains a formidable challenge. While end-to-end policies often lack the structural priors needed for e
arXiv:2511.09149v4 Announce Type: replace Abstract: While natural language is the de facto communication medium for LLM-based agents, it presents a fundamental constraint. The process of downsampling
arXiv:2604.14267v1 Announce Type: new Abstract: Search agents extend Large Language Models (LLMs) beyond static parametric knowledge by enabling access to up-to-date and long-tail information unavaila