Knowledge catalogue
arXiv:2605.24084v1 Announce Type: cross Abstract: Shapley additive explanations (SHAP) are widely recognised as computationally intractable for neural networks, since they induce an exponential search
arXiv:2605.26081v1 Announce Type: new Abstract: Deep research agents face vast, interdependent, and pervasively uncertain information. Existing systems explore what evolving intermediate representatio
Hugging Face shared insights and presentation slides detailing their process for generating 1 trillion tokens of synthetic data, offering a technical overview of their data generation methodology. The
arXiv:2605.23914v1 Announce Type: cross Abstract: Agentic workflows interleave configurable LLM stages with tool stages and often include retries or refinement loops. Existing workflow managers profil
arXiv:2605.25388v1 Announce Type: new Abstract: Nucleotide sequences constitute the fundamental genetic basis of biological systems, rendering viral genomic analysis critical for biomedical advancemen
arXiv:2605.24449v1 Announce Type: cross Abstract: Although quadcopters boast impressive traversal capabilities enabled by their omnidirectional maneuverability, the need for continuous pilot control i
arXiv:2605.25820v1 Announce Type: new Abstract: Diffusion-based multimodal large language models (dMLLMs) decode by iteratively predicting tokens at multiple masked positions in parallel. This turns e
arXiv:2509.25339v3 Announce Type: replace-cross Abstract: Is basic visual understanding really solved in state-of-the-art VLMs? We present VisualOverload, a slightly different visual question answerin
arXiv:2605.24031v1 Announce Type: cross Abstract: We study the reconstruction of implied volatility surfaces from sparse and noisy option quotes using deep learning models under no-arbitrage constrain
arXiv:2510.15514v3 Announce Type: replace Abstract: Reinforcement Learning from AI Feedback (RLAIF) relies on LLM judges as preference measurement instruments, yet these instruments are fundamentally
Plate tectonics recycles oxygen into Earth's mantle through subduction, with oxygen-rich fluids from serpentinite rocks being transported deep into the planet as tectonic plates sink. The rapid format
We aren’t going to do this again so quickly, are we? Rising demand results in higher costs. Higher costs result in lower demand. It is almost like some sort of equilibrium is being achieved. But there
We have, as far as I can tell, no good tests of the productivity impact of the autonomous coding tools that appeared starting in December 2025. Every paper out there is from prior to the Claude Code/C
we just revamped the create_agent docs! the new agents page shows how to build a custom harness for your use case w/ create_agent as an easy entrypoint start w/ your prompt and tools, then add middlew
> … [W]e keep finding things that are mysterious, even unsettling. We find structures that mirror results from human neuroscience. We find evidence of introspection. We find internal states that funct
We sat down with DeepMind CEO @demishassabis to find out how close we are to AGI, curing every disease with AI, and human meaning post-AGI. Full interview below, and the rundown is coming to the newsl
arXiv:2605.25385v1 Announce Type: cross Abstract: Camouflaged object detection (COD) from a single image is a challenging task due to the high similarity between objects and their surroundings. Existi
Apple's 599 MacBook Neo launched in March 2026 at approximately half the price of the MacBook Air, directly competing with lower-cost Windows PCs and triggering significant industry reaction. PC maker
We’ve shipped a security-guidance plugin for Claude Code that helps identify and fix vulnerabilities as you’re writing code. Available for all Claude Code users. Install from the plugin marketplace (/
arXiv:2605.24524v1 Announce Type: cross Abstract: In non-invasive neural language decoding, results can be inflated by sources that are not stimulus-evoked neural evidence: decoder priors, embedding-b
arXiv:2605.25517v1 Announce Type: new Abstract: AI answer engines generate answers from retrieved pages but cite only a few sources. This makes visibility depend not just on ranking, but on being cite
arXiv:2509.21592v2 Announce Type: replace-cross Abstract: We consider the problem of forecasting motion from a single image, i.e., predicting how objects in the world are likely to move, without the a
arXiv:2605.25988v1 Announce Type: new Abstract: Medical RAG needs evidence-grounded claims, so plugging a claim-level NLI checker into retrieval-augmented RL is intuitive. extbf{We find that the check
arXiv:2510.16435v2 Announce Type: replace-cross Abstract: With the growing use of large language models and conversational interfaces in human-robot interaction, robots' ability to answer user questio
Financial operations, known as FinOps, are undergoing a quiet shift — from managing cloud costs to shaping business decisions based on AI-driven insights. The practice is now an essential tool for man
arXiv:2605.25794v1 Announce Type: new Abstract: Early-warning models built from Learning Management System (LMS) logs aim to predict end-of-course outcomes early enough to enable timely learner suppor
arXiv:2605.23932v1 Announce Type: new Abstract: Despite strong medical benchmark accuracy, LLMs can exhibit severe multi-turn sycophancy in clinical dialogue, abandoning initial correct diagnosis unde
arXiv:2605.25981v1 Announce Type: new Abstract: We document an empirical phenomenon in chain-of-thought and ReAct agents driven by ten large language models from seven architecture families: meaning-b
arXiv:2605.24202v1 Announce Type: new Abstract: Multi-agent LLM workflows route inference through specialized roles to lift end-task accuracy, but jointly training those roles with reinforcement learn
arXiv:2605.24296v1 Announce Type: new Abstract: We study when LLM-generated synthetic data helps low-resource multi-label patent classification, separating true synthetic value from the confound that
arXiv:2605.26046v1 Announce Type: cross Abstract: Customizing an LLM judge to a specific task or domain often involves optimizing its prompt across multiple evaluation criteria simultaneously. Textual
When I woke up this morning I didn't think I'd be spending a bunch of time today getting familiar with Catholic theology, but here we are. Notes on Pope Leo XIV's encyclical on AI. https://simonwillis
arXiv:2605.25629v1 Announce Type: new Abstract: Weak-to-strong (W2S) generalization is a promising framework for scalable oversight, yet existing evaluations often test students under matched train--t
arXiv:2605.25304v1 Announce Type: new Abstract: Concept Bottleneck Models (CBMs) have emerged as a cornerstone approach for interpretable machine learning, providing human-understandable intermediate
arXiv:2605.24667v1 Announce Type: new Abstract: Mean cross-entropy is the standard validation metric for language models, but it can fail to track model quality during training. We examine this in two
arXiv:2605.24902v1 Announce Type: cross Abstract: Reasoning-enabled LLMs perform strongly on medical reasoning benchmarks, but it remains unclear whether these gains transfer to structured clinical do
arXiv:2605.25832v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as proposal generators for evolutionary robot design, yet most loops remain memoryless: simulator r
arXiv:2605.25864v1 Announce Type: cross Abstract: Large Language Models (LLMs) have achieved remarkable advancements in reasoning capabilities empowered by Reinforcement Learning with Verifiable Rewar
arXiv:2605.24069v1 Announce Type: cross Abstract: The rise of tool-using Large Language Model (LLM) agents, standardized by protocols like the Model Context Protocol (MCP), has unlocked unprecedented
when you think about it SpaceX has cumulatively lost a lot less than OpenAI so maybe it’s a bargain? or maybe we just shouldn’t value companies at a trillion dollars until they actually show evidence
arXiv:2605.24579v1 Announce Type: new Abstract: Long-context memory systems often fail under fixed budgets, but end-to-end evaluation does not reveal whether evidence was discarded during compression
arXiv:2510.08609v3 Announce Type: replace-cross Abstract: Developers consistently use version constraints to specify acceptable versions of the dependencies for their project. Pinning dependencies can
arXiv:2509.10452v2 Announce Type: replace Abstract: Pretrained automatic speech recognition (ASR) models such as Whisper perform well but still need domain adaptation to handle unseen parlance. In man
This post likely features a comparison of two similar images, designs, or creations side-by-side asking viewers to judge which version is superior—a common format on social media for crowdsourcing opi
arXiv:2605.24737v1 Announce Type: cross Abstract: Current approaches to AI compliance treat conformity as a binary, audit-time verdict rather than a continuous, measurable property of production syste
arXiv:2605.26070v1 Announce Type: new Abstract: Annotating speaker attributes from text is inherently ambiguous, particularly in multilingual settings where demographic and social cues are implicit an
arXiv:2605.25256v1 Announce Type: new Abstract: Aligning AI systems with organizational decision-making is typically framed as a single-target problem: make the model behave like the organization. We
arXiv:2602.10538v3 Announce Type: replace-cross Abstract: Agentic theorem provers combine a reasoning model, retrieval, search, and a proof assistant verifier, yet it remains unclear which components
arXiv:2605.23972v1 Announce Type: new Abstract: Large language models achieve strong performance in language generation and knowledge-intensive tasks, yet remain limited in settings requiring causal r
arXiv:2601.22984v2 Announce Type: replace Abstract: Diagnosing failure patterns in Deep Research Agents (DRAs) remains a critical challenge. Existing benchmarks predominantly rely on end-to-end evalua
arXiv:2605.24074v1 Announce Type: cross Abstract: Fisheye cameras are increasingly adopted in robotics for near-field manipulation, navigation, and immersive perception, yet indoor depth benchmarks wi
The Windows 95 classic 3D Space Cadet pinball game is being converted from its original digital format into a functional physical pinball machine. The recreation uses largely 3D-printed components inc
arXiv:2605.24651v1 Announce Type: cross Abstract: We propose a Weak-form Physics-Informed Neural Operator (WINO), a data-free framework that combines the efficiency of neural operators with the geomet
arXiv:2512.24000v3 Announce Type: replace Abstract: Distinguishing fake or untrue news from satire or humor poses a unique challenge due to their overlapping linguistic features and divergent intent.
arXiv:2605.24658v1 Announce Type: new Abstract: This work introduces the Wavelet-Laplace Neural Operator (WLNO), a novel neural operator that fuses Haar wavelet multi-scale spatial decomposition with
arXiv:2605.24585v1 Announce Type: new Abstract: Language models are typically trained to predict the next token in a sequence. Here, we explore an alternative predictive principle from reinforcement l
Visual Fold is a tool for simple visual organization of ComfyUI workflows that does not turn selected nodes into a subgraph or change workflow logic. Group folding and node alignment features enable c
arXiv:2605.24719v1 Announce Type: cross Abstract: Large Language Models (LLMs) have changed the possibilities of Interactive Storytelling systems that process free-text user input. However, as more of
arXiv:2602.06508v2 Announce Type: replace Abstract: Reinforcement learning (RL) can refine Vision-Language-Action (VLA) policies beyond behavior cloning, but real-world RL remains expensive due to ext
arXiv:2502.08047v5 Announce Type: replace Abstract: Recent progress in GUI agents has substantially improved visual grounding, yet robust planning remains challenging, particularly when the environmen