Knowledge catalogue
arXiv:2602.18792v3 Announce Type: replace Abstract: Visual counterfactual explanations aim to reveal the minimal semantic modifications that can alter a model's prediction, providing causal and interp
arXiv:2604.21119v1 Announce Type: cross Abstract: Rings like gold, thuds like wood! The sound we hear in a scene is shaped not only by the spatial layout of the environment but also by the materials o
arXiv:2604.21916v1 Announce Type: new Abstract: As frontier language models attain near-ceiling performance on static mathematical benchmarks, existing evaluations are increasingly unable to different
arXiv:2604.20848v1 Announce Type: cross Abstract: Large Language Model (LLM)-based recommendation systems have demonstrated remarkable capabilities in understanding user preferences and generating per
arXiv:2604.21026v1 Announce Type: new Abstract: Deploying large language models to heterogeneous hardware is often constrained by memory, not compute. We introduce MCAP (Monte Carlo Activation Profili
arXiv:2604.21365v1 Announce Type: cross Abstract: Multi-domain detection of the machine-generated code snippets in various programming languages is a challenging task. SemEval-2026 Task~13 copes with
arXiv:2604.21268v1 Announce Type: cross Abstract: Graphical User Interface (GUI) grounding requires mapping natural language instructions to precise pixel coordinates. However, due to visually homogen
arXiv:2603.18740v2 Announce Type: replace-cross Abstract: Automated Code Review (ACR) systems integrating Large Language Models (LLMs) are increasingly adopted in software development workflows, rangi
arXiv:2604.21564v1 Announce Type: new Abstract: Large language models increasingly shape the information people consume: they are embedded in search, consulted for professional advice, deployed as age
Fossilized jaws reveal that enormous octopuses growing up to 19 meters long were top predators in the oceans during the Cretaceous Period, potentially making them the largest marine animals and invert
Matt Day / Bloomberg: Meta and Amazon reach a multibillion-dollar, multiyear deal for Meta to rent hundreds of thousands of Amazon's Graviton chips for its AI inference needs — Amazon.com Inc. and Met
Ina Fried / Axios: Meta inks deal to use more Amazon chips — Meta on Friday announced a deal to use Amazon-designed chips to help deliver its next generation of AI models. … - The new pact, which buil
arXiv:2507.01829v2 Announce Type: replace-cross Abstract: Multi-timescale sequence modeling relies on capturing both local fast dynamics and global slow context; yet, maintaining these capabilities un
arXiv:2604.21011v1 Announce Type: new Abstract: Micro-actions are subtle, localized movements lasting 1-3 seconds such as scratching one's head or tapping fingers. Such subtle actions are essential fo
arXiv:2604.21326v1 Announce Type: cross Abstract: Universal Multimodal Retrieval (UMR) aims to map different modalities (e.g., visual and textual) into a shared embedding space for multi-modal retriev
arXiv:2309.07176v5 Announce Type: replace Abstract: In consequential domains, it is often impossible to compel individuals to take treatment, so that optimal policy rules are merely suggestions in the
arXiv:2604.21092v1 Announce Type: new Abstract: Integrating Large Language Models (LLMs) into complex software systems enables the generation of human-understandable explanations of opaque AI processe
arXiv:2604.21767v1 Announce Type: new Abstract: Online misinformation is one of the most challenging issues lately, yielding severe consequences, including political polarization, attacks on democracy
arXiv:2604.21489v1 Announce Type: cross Abstract: Multi-modal trajectory generation is essential for safe autonomous driving, yet existing diffusion-based planners suffer from high inference latency d
arXiv:2510.18731v2 Announce Type: replace-cross Abstract: Large Language Models demonstrate strong capabilities in single-turn instruction following but suffer from Lost-in-Conversation (LiC), a degra
arXiv:2604.20858v1 Announce Type: cross Abstract: Sequential recommendation has rapidly advanced in click-through rate prediction due to its ability to model dynamic user interests. A key challenge, h
arXiv:2604.21370v1 Announce Type: new Abstract: We present a systematic study of multilingual polarization detection across 22 languages for SemEval-2026 Task 9 (Subtask 1), contrasting multilingual g
Ollama announced DeepSeek-v4-flash, a lightweight variant of the DeepSeek-v4 model, now available in their model library for local deployment and integration. The model page provides documentation, us
Models are changing really fast, often in ways that will break your product and technical assumptions. There's no way around this – the only way forward is to relentlessly iterate to make sure you're
arXiv:2604.21836v1 Announce Type: cross Abstract: Neural networks exhibit a remarkable degree of representational convergence across diverse architectures, training objectives, and even data modalitie
Replit implements a defense-in-depth security strategy to protect user applications across multiple architectural layers of their platform. The blog post details the security measures and protocols Re
More of my notes on DeepSeek V4 - the really big news is the pricing: both DeepSeek-V4-Flash and DeepSeek-V4-Pro are the cheapest models in their categories while benchmarking close to the frontier mo
CursorBench is a benchmarking tool or evaluation framework developed by Cursor, likely designed to measure and compare the performance of AI code completion or development features. The post provides
arXiv:2604.21155v1 Announce Type: new Abstract: Intrinsic motivations are receiving increasing attention, i.e. behavioral incentives that are not engineered, but emerge from the interaction of an agen
arXiv:2604.21096v1 Announce Type: cross Abstract: Tip-of-the-Tongue (ToT) retrieval benchmarks have largely focused on English, limiting their applicability to multilingual information access. In this
arXiv:2604.21637v1 Announce Type: new Abstract: Where and how language models (LMs) are deployed determines who can benefit from them. However, there are several challenges that prevent effective depl
arXiv:2512.18908v2 Announce Type: replace Abstract: Mass Casualty Incidents can overwhelm emergency medical systems and resulting delays or errors in the assessment of casualties can lead to preventab
arXiv:2603.12845v2 Announce Type: replace Abstract: Predicting enzyme kinetic parameters quantifies how efficiently an enzyme catalyzes a specific substrate under defined biochemical conditions. Canon
arXiv:2604.21810v1 Announce Type: new Abstract: We address the ambiguities in the super-resolution problem under translation. We demonstrate that combinations of low-resolution images at different sca
arXiv:2511.20697v4 Announce Type: replace-cross Abstract: Understanding complete musical scores entails integrated reasoning over pitch, rhythm, harmony, and large-scale structure, yet the ability of
Ethan Mollick documents his first attempts at using DeepSeek v4's expert mode to generate TiKZ code for creating unicorn graphics, sharing results from the DeepSeek website's v4 Pro interface. The pos
arXiv:2604.21138v1 Announce Type: cross Abstract: Multi-robot control in cluttered environments is a challenging problem that involves complex physical constraints, including robot-robot collisions, r
Necessity is the mother of kv-cache optimisation I’m still amazed that DeepSeek, Kimi, and Qwen can train very strong LLMs with far fewer and often nerfed NVIDIA GPUs, or even Huawei chips. DeepSeek V
arXiv:2604.21896v1 Announce Type: new Abstract: This paper introduces a new paradigm for AI game programming, leveraging large language models (LLMs) to extend and operationalize Claude Shannon's taxo
arXiv:2604.21753v1 Announce Type: cross Abstract: Simulations of crystal growth are performed by using Convolutional Recurrent Neural Network surrogate models, trained on a dataset of time sequences c
arXiv:2604.21053v1 Announce Type: cross Abstract: Robotic systems operating in human environments must reason about how object interactions evolve over time, which actions are currently being performe
arXiv:2604.21222v1 Announce Type: cross Abstract: Glassy silica is a foundational material in optics and electronics, yet accurately predicting its medium-range order (MRO) remains a major challenge f
New episode of The Information Bottleneck is out, this time with @liuzhuang1234 (Princeton). We talked about ConvNeXt and whether architecture still matters; dataset bias and what 'good data' actually
New Frontier LLM Orchestrator Model @SakanaAILabs The fugu model series provides a novel paradigm for test-time scaling. The models are trained to call LLMs and infer not only which individual model i
Grok achieved top performance on the τ-voice Bench voice AI benchmark, scoring 67.3% overall and leading in specific domains including retail (62.3%) and airline (66%) categories. The announcement was
arXiv:2506.05590v3 Announce Type: replace-cross Abstract: Recent advances have established the identifiability of a directed acyclic graph (DAG) under additive noise models (ANMs), spurring the develo
Terje Solsvik / Reuters: Norway plans to ban children from using social media until they turn 16; the government says it will introduce a bill in parliament by the end of 2026 — Norway said on Friday
arXiv:2510.20064v2 Announce Type: replace Abstract: Speculative decoding is widely used in accelerating large language model (LLM) inference. In this work, we focus on the online draft model selection
Not bad I tested the same prompt on both Grok 4.3 and GPT 5.5: “Count to 10 starting from 11” ChatGPT 5.5 gave the obvious 11–20 Grok 4.3 gave 11, 10 and explained why going backwards was the only log
arXiv:2601.20706v2 Announce Type: replace-cross Abstract: Diffusion-based LLMs (dLLMs) fundamentally depart from traditional autoregressive (AR) LLM inference: they leverage bidirectional attention, b
Number of people who go bankrupt every year because of medical bills or illness-related work loss: 🇦🇺 0 🇨🇦 0 🇩🇰 0 🇫🇮 0 🇫🇷 0 🇩🇪 0 🇮🇸 0 🇮🇪 0 🇮🇹 0 🇯🇵 0 🇳🇱 0 🇳🇴 0 🇵🇹 0 🇪🇸 0 🇸🇪 0 🇬🇧 0 🇺🇸 530,000 There’s a
Jordan Novet / CNBC: Nvidia stock jumps 4.3% to close at a record for the first time since Oct., pushing Nvidia's market cap past 5T, as a rally in Intel pushed chipmakers higher — Nvidia shares close
🐳Ollama is working to have DeepSeek-V4-Pro and Flash available on Ollama's cloud. 🚀 DeepSeek-V4 Preview is officially live & open-sourced! Welcome to the era of cost-effective 1M context length. 🔹 Dee
arXiv:2604.20911v1 Announce Type: cross Abstract: LLM agents deployed in production operate under operator-defined behavioral policies (system-prompt instructions such as prohibitions on credential di
arXiv:2604.21575v1 Announce Type: new Abstract: Fitting an underlying body model to 3D clothed human assets has been extensively studied, yet most approaches focus on either single-modal inputs such a
arXiv:2604.21204v1 Announce Type: cross Abstract: In this work, we develop a novel reasoning approach to enhance the performance of large language models (LLMs) in future occupation prediction. In thi
arXiv:2604.21825v1 Announce Type: cross Abstract: For continuous-time dynamical systems with reversible trajectories, the nowhere-vanishing eigenfunctions of the Koopman operator of the system form a
arXiv:2603.27406v2 Announce Type: replace Abstract: In this paper, the relationship between probabilistic graphical models, in particular Bayesian networks, and causal diagrams, also called structural
arXiv:2604.21602v1 Announce Type: cross Abstract: Reservoir computing (RC) is an emerging recurrent neural network architecture that has attracted growing attention for its low training cost and modes
One of my favorite things about Sakana Fugu is the recursive test-time scaling. When allowed to call itself recursively, it reads its own prior output and spins up corrective workflows on the fly. We