Knowledge catalogue
arXiv:2407.04573v4 Announce Type: replace-cross Abstract: Dense vector retrieval is an important building block of modern machine learning systems, underlying applications ranging from semantic search
arXiv:2605.22975v1 Announce Type: new Abstract: We ask whether large language models (LLMs) treat queries about religious conversion symmetrically. The answer is no. When asked for advice on hypotheti
neurosymbolic by @swarat et al for the Erdos win, with much more careful, quantitative work than openai’s in hindsight i wonder whether OpenAI rushed theirs out, knowing this was coming? Another 9 ope
Well over 300,000 people seem to have felt the same way, roon’s attack, arrogant, misleading, and unprovoked, did OpenAI no favors. @GaryMarcus roon's attack on you is really making me think less of h
// Adapt the Interface, Not the Model // I am fascinated by the results across my cheap-model-plus-good-harness builds. This new paper also shows good signs of the code-as-agent-harness thesis. The id
arXiv:2605.21615v1 Announce Type: cross Abstract: Existing binary corpora typically capture only one or two axes of binary variation: they either provide cross-compiler builds without a temporal axis,
The search results show information about llama.cpp releases but don't contain specific details about build b9297. Based on the context and numbering (b9297 is a recent build after b9294), b9297 is li
arXiv:2510.10129v2 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) systems suffer from severe time-to-first-token (TTFT) bottlenecks due to long input sequences. Existing KV cach
arXiv:2605.21928v1 Announce Type: new Abstract: Estimating treatment effects from observational data requires choosing an adjustment set, but valid adjustment depends on an unknown causal graph. Graph
arXiv:2603.02604v2 Announce Type: replace Abstract: We introduce Heterogeneous Agent Collaborative Reinforcement Learning (HACRL), a new Reinforcement Learning from Verifiable Reward (RLVR) problem th
arXiv:2605.21773v1 Announce Type: cross Abstract: Recent benchmark efforts have advanced the evaluation of large language models (LLMs) in cybersecurity, including tasks such as penetration testing an
arXiv:2605.21770v1 Announce Type: new Abstract: Large language models frequently produce errors in reasoning tasks despite possessing the underlying knowledge required for correct reasoning. One possi
to everyone that's using ai to generate their tweets. we know. i know you think you're being lowkey. i know you might be switching around some words, and removing em dashes. but it's so obvious. anyon
arXiv:2605.22715v1 Announce Type: cross Abstract: As wearable and mobile devices become increasingly embedded in daily life, they offer a practical way to continuously sense human motion in the wild.
arXiv:2605.22435v1 Announce Type: new Abstract: Hate speech and misinformation frequently co-occur online, amplifying prejudice and polarization. Given their scale, using Large Language Models (LLMs)
arXiv:2605.21728v1 Announce Type: cross Abstract: Image captioning evaluation remains a significant challenge, as vision-language models evolve toward more challenging capabilities such as generating
arXiv:2605.21712v1 Announce Type: new Abstract: Transportation safety analysis requires integrating crash records, roadway attributes, and geospatial data through GIS-based workflows, but access remai
arXiv:2602.08028v1 Announce Type: cross Abstract: To address the instability of unguided reasoning paths in standard Chain-of-Thought prompting, recent methods guide large language models (LLMs) by fi
Eight key points from the most recent essay in the “AI as Normal Technology” series by @sayashk and me. Do AI Risks Require Extraordinary Government Intervention? 1. There is general consensus that AI
arXiv:2401.00139v3 Announce Type: replace-cross Abstract: This paper introduces a causal attribution model to enhance the interpretability of large language models (LLMs) and improve their causal reas
arXiv:2605.22391v1 Announce Type: cross Abstract: We present Epicure, a family of three sibling skip-gram ingredient embeddings retrained from scratch on a multilingual recipe corpus. We aggregate 4.1
arXiv:2507.23773v3 Announce Type: replace-cross Abstract: What does it mean to plan? Current agentic systems, whether scaffolded workflows or end-to-end policies, rely on reactive decision-making: sel
arXiv:2605.20874v1 Announce Type: new Abstract: Enterprise agents are increasingly expected to operate autonomously across tools and interfaces, yet production deployments require governance by constr
arXiv:2605.21496v1 Announce Type: cross Abstract: Frontier language models are being deployed into clinical workflows faster than the infrastructure to evaluate them safely. Static medical-QA benchmar
arXiv:2605.20704v1 Announce Type: cross Abstract: Autonomous AI agents that spawn sub-agent swarms create a safety gap: existing credential revocation mechanisms, OAuth~2.0 introspection, OCSP, and W3
i suspect that this is a wild underestimate, both ignoring the costs in developing the model and ignoring the fact that many questions may well have been posed that didn’t succeed. If this is true, us
arXiv:2602.02660v3 Announce Type: replace Abstract: A critical bottleneck in automating AI research is the execution of complex machine learning engineering (MLE) tasks. MLE differs from general softw
arXiv:2605.22469v1 Announce Type: new Abstract: Evaluating single-concept personalization in text-to-image diffusion requires measuring both concept preservation, which captures identity fidelity to a
arXiv:2605.22269v1 Announce Type: new Abstract: Long streaming video QA remains challenging due to growing visual tokens and limited reasoning length of large language models (LLMs). KV-caching stores
arXiv:2506.19500v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) increasingly act as function-call agents that invoke external tools to tackle tasks beyond their static knowledge
NEW paper worth reading. A full agentic workflow can be distilled into model weights and run at roughly 100x lower inference cost while preserving near-frontier task quality. The workflow includes mul
arXiv:2605.20423v1 Announce Type: new Abstract: Large Language Models (LLMs) perform well on many language tasks, but their Theory of Mind (ToM) reasoning is still uneven in complex social settings. E
arXiv:2605.21726v1 Announce Type: new Abstract: The generative nature of Large Language Models (LLMs) is reflected in the conditional probabilities they compute to sample each response token given the
This is one of the things I dislike about managed agents. Is it the best DX? yes. Is it now much, much more usable because it's bring your own sandbox? yes (most startups now have Sandbox credits and
arXiv:2605.20190v1 Announce Type: new Abstract: Iterative industrial design-simulation optimization is bottlenecked by the CAD-CAE semantic gap: translating simulation feedback into valid geometric ed
arXiv:2605.22355v1 Announce Type: new Abstract: Public transit route planning traditionally depends on structured map infrastructure and complex routing engines, and no existing dataset supports train
arXiv:2605.22403v1 Announce Type: new Abstract: Surface electromyography (sEMG) signal-based activity recognition has attracted increasing research attention in recent years. To develop accurate sEMG
arXiv:2605.06597v2 Announce Type: replace Abstract: Self-distillation (SD) offers a promising path for adapting large language models (LLMs) without relying on stronger external teachers. However, SD
arXiv:2605.21102v1 Announce Type: new Abstract: Academic researchers need efficient and reliable methods for collecting high-quality information from trusted sources, but modern tools for AI-assisted
Release b9255 of llama.cpp features a Hexagon HMX quantized matmul rework (#23368), including updates to debug logging, dequantization logic using HVX vectors, removal of non-pipelined quantization op
arXiv:2605.20684v1 Announce Type: new Abstract: Corporate credit underwriting requires analysts to extract actionable evidence from long, heterogeneous financial documents spanning hundreds of pages a
In this post, you will learn how to implement Recursive Language Models (RLM) using Amazon Bedrock AgentCore Code Interpreter and the Strands Agents SDK. By the end, you will know how to process docum
arXiv:2605.21029v1 Announce Type: new Abstract: Utilizing LLMs for automated taxonomy construction presents a clear opportunity for the comprehensive, yet efficient mapping of potentially complex doma
arXiv:2506.04042v2 Announce Type: replace Abstract: Knowledge editing is pivotal for efficiently updating the parametric memory of Large Language Models (LLMs), enabling them to function as evolving a
Command A+ is available on @huggingface with W4A4 quantization 🤗 Cut your serving footprint dramatically with virtually zero performance degradation. Try it now: https://huggingface.co/CohereLabs/comm
arXiv:2605.20247v1 Announce Type: cross Abstract: Catastrophic forgetting remains a major obstacle to continual learning in large language models (LLMs) and vision--language models (VLMs). Although Mi
arXiv:2605.20628v1 Announce Type: new Abstract: Biomedical abstracts play a critical role in downstream NLP applications, such as information retrieval, biocuration, and biomedical knowledge discovery
arXiv:2605.20591v1 Announce Type: new Abstract: Medical large language models (LLMs), including custom medical GPTs (MedGPTs) and open-source models, are increasingly deployed on web platforms to prov
arXiv:2605.20448v1 Announce Type: new Abstract: Vision--language models reliably name objects in a scene, but do they represent the 3D layout those objects inhabit? We introduce a 3,034-sample human-c
arXiv:2605.21369v1 Announce Type: new Abstract: This paper describes the fifth edition of the Shared Task on Multilingual Coreference Resolution, held in conjunction with the CODI-CRAC 2026 workshop.
Gated DeltaNet-2 is here. 🚀 🔥 New paper: Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention Gated DeltaNet-2 outperforms KDA and Mamba-3, the latest and best recurrent architectures, hea
arXiv:2605.20896v1 Announce Type: cross Abstract: Defending against today's increasingly sophisticated cyberattacks requires security analysts to continuously translate evolving attacker tradecraft in
arXiv:2605.21076v1 Announce Type: new Abstract: Grading German legal exam solutions faces growing volumes and a shortage of qualified graders, delaying feedback and creating a bottleneck. At the same
arXiv:2605.21061v1 Announce Type: new Abstract: Existing Driving VLAs predict trajectories while largely ignoring their visual tokens -- a phenomenon we trace not to insufficient training but to a str
arXiv:2605.20469v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly used for medical image interpretation, yet they frequently hallucinate, generating clinically plausible b
It’s crazy that OpenAI and xAI were built partly as ways to mitigate @demishassabis’s power and how both are more reckless and less focused on the good part, viz AI for science. And then Anthropic was
arXiv:2605.21160v1 Announce Type: new Abstract: The discovery of first integrals is of fundamental scientific importance for understanding conservation laws in dynamical systems. However, existing sym
arXiv:2605.20729v1 Announce Type: new Abstract: Accurate evaluation of conversational retrieval is pivotal for advancing Retrieval-Augmented Generation (RAG) systems. However, existing conversational
arXiv:2605.21225v1 Announce Type: new Abstract: We address the problem of making a pre-trained reinforcement learning (RL) policy safety-aware by incorporating cost constraints without retraining it f
arXiv:2605.21403v1 Announce Type: new Abstract: Agreement attraction errors, in which a verb erroneously agrees with an intervening noun rather than its grammatical head, are amplified by morphologica