Unlimited OCR Works
arXiv:2606.23050v1 Announce Type: new Abstract: Recently, end-to-end OCR models, exemplified by DeepSeek OCR, have once again thrust OCR into the spotlight. A widely held view is that employing a larg
Knowledge catalogue
arXiv:2606.23050v1 Announce Type: new Abstract: Recently, end-to-end OCR models, exemplified by DeepSeek OCR, have once again thrust OCR into the spotlight. A widely held view is that employing a larg
arXiv:2606.14970v2 Announce Type: replace Abstract: Fine-tuning large language models (LLMs) has become a central application of modern optimization, enabling pretrained models to adapt to diverse dow
Another new idea to push the state of AI architectures forward. Sakana released a model that effectively uses a mixture of models to get work done. You get a single API but then the work gets farmed o
>> Scalable Evaluation for AI Agents << If you run agent evaluation in production, this one is worth your time. It shows that front-loading human judgment into reusable evaluation assets is useful. Bu
sqlite-utils is my combined Python library and CLI tool for working with SQLite databases. It provides an extensive set of higher-level operations on top of Python's default sqlite3 package, including
'Verifiable results (True/False) combined with a solution space exploration technique' - very well put. Crux of neuro-symbolic #ai, what @GaryMarcus has been shouting about it for decades. Crux of the
Vercel’s open-source agent framework — durable sessions, sandboxes, HITL, tools/skills as files; positioned as Next.js for agents.
arXiv:2509.11575v3 Announce Type: replace Abstract: Time series reasoning treats time as a first-class axis and incorporates intermediate evidence directly into the answer. This survey defines the pro
arXiv:2606.11869v1 Announce Type: cross Abstract: Custom AI agents areagents that live inside their own application, talk to their own data and tools, enforce their own security boundaries, and carry
arXiv:2606.11447v1 Announce Type: new Abstract: Recent anecdotal evidence suggests that AI coding agents can reproduce published findings when provided with original data and code; yet systematic eval
arXiv:2606.12342v1 Announce Type: cross Abstract: Domain fine-tuning degrades the safety of large language models: fine-tuned specialists readily comply with harmful prompts framed in domain language.
arXiv:2606.11218v1 Announce Type: cross Abstract: Ethical deliberation is often misunderstood as a search for single right or wrong answers, creating difficulties for non-ethically trained personnel w
arXiv:2606.11459v1 Announce Type: cross Abstract: Large Language Models are highly sensitive to prompt formulation, necessitating automatic prompt optimization to unlock their full potential. While ev
arXiv:2606.11874v1 Announce Type: new Abstract: With the development of autonomous driving systems, mining high-value, safety-critical, and planning-relevant scenarios from large-scale driving logs ha
arXiv:2606.12370v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become a key component in modern large language models, yet the rollout stage remains the key bottleneck in RL trainin
arXiv:2606.11678v1 Announce Type: new Abstract: Problem, Research Strategy, and Findings: The rise of large language models (LLMs) raises a key question for urban planning: which forms of professional
arXiv:2507.11688v4 Announce Type: replace Abstract: Contemporary large models often exhibit behaviors suggesting the presence of low-level primitives that compose into modules with richer functionalit
arXiv:2506.20040v3 Announce Type: replace-cross Abstract: Interpreting language models remains challenging due to the existence of residual stream, which linearly mixes and duplicates features across
arXiv:2606.11616v1 Announce Type: new Abstract: High-quality training data is essential for the success of machine learning models. However, real-world datasets often contain mixed types of errors ari
arXiv:2606.12114v1 Announce Type: new Abstract: Sensitive personal information can appear in large-scale pre-training corpora for large language models (LLMs). Detecting and filtering such information
arXiv:2606.11745v1 Announce Type: cross Abstract: Visual causal reasoning is essential for understanding and intervening in the physical world, requiring identification of causal variables from visual
arXiv:2606.11744v1 Announce Type: cross Abstract: Large language models are now widely used for everyday learning, but the underlying interactions are typically unstructured chats rather than followin
arXiv:2603.06910v2 Announce Type: replace Abstract: Multilingual large language models (LLMs) are increasingly used in socially sensitive mental health contexts, including support chatbots, screening,
arXiv:2606.11786v1 Announce Type: new Abstract: Large Language Models (LLMs) offer new potential for translation tasks but often experience performance degradation when handling low-resource languages
arXiv:2606.11724v1 Announce Type: new Abstract: Theory of Mind (ToM) reasoning requires inferring agents' beliefs from partial and asymmetric observations, which remains an open challenge for LLMs. Ex
arXiv:2606.11431v1 Announce Type: new Abstract: Mirror Descent (MD) extends Gradient Descent (GD) beyond Euclidean geometry and has recently reappeared as a lens for KL-regularized policy optimization
arXiv:2606.12106v1 Announce Type: cross Abstract: This paper presents our solution to the 2026 SoccerNet VQA Challenge. We first develop a cost-effective data synthesis pipeline driven by a Vision-Lan
arXiv:2606.11199v1 Announce Type: cross Abstract: We present NightFeats, a structured multi-agent retrieval-augmented generation (RAG) system submitted to the MMU-RAGent competition at NeurIPS 2025, w
arXiv:2505.15201v5 Announce Type: replace-cross Abstract: Reinforcement Learning (RL) algorithms sample multiple n>1 solution attempts for each problem and reward them independently. This optimizes fo
arXiv:2606.11605v1 Announce Type: cross Abstract: Predicting process-property relationships in manufacturing is often challenged by high experimental costs and the limited interpretability of complex
arXiv:2602.02229v2 Announce Type: replace Abstract: We study the problem of monitoring model performance in dynamic environments where labeled data are limited. To this end, we propose prediction-powe
arXiv:2606.11275v1 Announce Type: cross Abstract: Rotary Position Embeddings (RoPE) make attention scores position-relative but leave the value pathway position-blind: the message sent by a value toke
arXiv:2606.11304v1 Announce Type: cross Abstract: We introduce SPADE (SPlit And Delay Embeddings), an autoregressive transformer for sequences whose tokens carry multiple features. Rather than embeddi
arXiv:2606.12392v1 Announce Type: cross Abstract: Recently, large language models (LLMs) have achieved promising progress in the fields of classical Chinese translation and the generation of classical
arXiv:2606.12387v1 Announce Type: cross Abstract: Large Language Models (LLMs) have democratized database access through Text-to-SQL, but moving from prototypes to production remains difficult. Real d
arXiv:2606.11437v1 Announce Type: cross Abstract: Efficiently sampling from a complex probability distribution is a fundamental problem which has become increasingly pertinent in recent years with the
arXiv:2606.11945v1 Announce Type: new Abstract: This report describes our participation in SemEval-2026 Task 8 on multi-turn retrieval and question answering. The task evaluates conversational systems
arXiv:2606.12243v1 Announce Type: cross Abstract: Speculative decoding (SD) addresses the high inference costs of LLMs by having lightweight drafters generate candidates for large verifiers to validat
arXiv:2606.11350v1 Announce Type: new Abstract: Retrieval-augmented generation degrades when scaled to large, heterogeneous document collections, where dense similarity loses discriminative power, and
arXiv:2606.10489v1 Announce Type: new Abstract: Automated Planning is a subfield of Artificial Intelligence (AI) where the main objective is generating a sequence of actions, known as a plan, that hel
arXiv:2505.23851v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly applied to symbolic mathematics, yet existing evaluations often conflate pattern memorization wi
arXiv:2606.10716v1 Announce Type: cross Abstract: Pre-trained language models (PLMs) have achieved strong performance in keyphrase extraction (KPE), largely due to their ability to generate rich conte
arXiv:2606.10156v1 Announce Type: cross Abstract: As recommender systems transition toward agentic, multi-turn conversational interfaces, evaluation paradigms have struggled to keep pace. Current benc
arXiv:2606.10533v1 Announce Type: new Abstract: Audio-visual captioning generates natural language descriptions from video and audio content. Multimodal LLMs have advanced this task, but both modaliti
arXiv:2510.08622v2 Announce Type: replace Abstract: Software requirements are derived from a variety of elicitation techniques, many of which have a conversational nature, like interviews. However, ev
arXiv:2606.10752v1 Announce Type: new Abstract: Numerical solvers for partial differential equations (PDEs) are core computational tools in science and engineering. Building reliable PDE solvers requi
arXiv:2606.10064v1 Announce Type: cross Abstract: Small-model agentic post-training is bottlenecked less by the algorithm than by the trajectory substrate it consumes. Leading recipes (RLVR, group-rel
arXiv:2606.10808v1 Announce Type: new Abstract: Multi-pair robotic assembly in unstructured environments faces spatial interference and contact uncertainties. Existing paradigms fail to bridge cogniti
Release: datasette-agent 0.2a0 Highlights from the release notes: Tools can now ask the user questions mid-execution. Tools that declare a context parameter receive a ToolContext object, and await con
arXiv:2606.10400v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly deployed where answers must follow from what is in the image, yet they often answer from textual priors,
arXiv:2606.09878v1 Announce Type: new Abstract: Standard benchmarks report aggregate accuracy, but practitioners need to know which specific capabilities a model lacks. We introduce FailureScope, a be
arXiv:2606.11023v1 Announce Type: cross Abstract: Sequential recommendation aims to predict users' next interaction with items by analyzing their historical behavior. However, the limited quality of i
HISTORY LESSON: In 1968 the US, USSR, UK, France, and China signed the Nuclear Non-Proliferation Treaty, declaring nuclear weapons too dangerous for any more countries to build. All five already had t
If Claude Fable stops helping you, you'll never know Jonathon Ready highlights one of the more eyebrow-raising details from the 319 page system card for Fable 5 and Mythos 5. Here's a longer excerpt,
arXiv:2606.10358v1 Announce Type: cross Abstract: Learning Bayesian network (BN) structure from sparse discrete data is hard: when each instance records only a few variables, most variable pairs lack
arXiv:2606.10460v1 Announce Type: cross Abstract: Recent large language models (LLMs) have shown rapid progress in reading-based question answering (QA), where evidence is explicitly provided or can b
arXiv:2606.10974v1 Announce Type: new Abstract: The driving behavior of autonomous vehicles is typically governed by the cost function of their motion planner, which encodes objectives such as speed t
arXiv:2606.11167v1 Announce Type: new Abstract: Full-duplex spoken dialogue models can listen and speak simultaneously, making them a promising architecture for natural conversation. However, current
arXiv:2606.10583v1 Announce Type: cross Abstract: We present NOVA, an autonomous symbolic regression framework that identifies interpretable car-following and lane-change structures from raw trajector
arXiv:2606.10989v1 Announce Type: new Abstract: Large language model unlearning aims to suppress designated undesirable knowledge while preserving benign capabilities. Many unlearning objectives focus