Video-Zero: Self-Evolution Video Understanding
arXiv:2605.14733v1 Announce Type: new Abstract: Self-evolution offers a promising path for improving reasoning models without relying on intensive human annotation. However, extending this paradigm to
Knowledge catalogue
arXiv:2605.14733v1 Announce Type: new Abstract: Self-evolution offers a promising path for improving reasoning models without relying on intensive human annotation. However, extending this paradigm to
arXiv:2512.13399v2 Announce Type: replace Abstract: Crafting effective reward signals remains a central challenge in Reinforcement Learning (RL), especially for complex reasoning tasks. Existing autom
arXiv:2605.12682v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as reasoning modules in many applications. While they are efficient in certain tasks, LLMs often stru
arXiv:2505.12415v3 Announce Type: replace-cross Abstract: Tables present unique challenges for language models due to their structured row-column interactions, necessitating specialized approaches for
arXiv:2509.25239v3 Announce Type: replace-cross Abstract: Chain of thought (CoT) elicits reasoning in large language models by explicitly generating intermediate tokens. In contrast, latent thought re
arXiv:2605.11439v1 Announce Type: new Abstract: Rapid and accurate situational awareness is essential for effective response during natural disasters, where delays in analysis can significantly hinder
arXiv:2605.11011v1 Announce Type: new Abstract: Looped computation shows promise in improving the reasoning-oriented performance of LLMs by scaling test-time compute. However, existing approaches typi
arXiv:2605.12477v1 Announce Type: cross Abstract: LLM-based agents increasingly operate in persistent environments where they must store, update, and reason over information across many sessions. Whil
Databases have introduced new AI-powered SQL functions which take natural language instructions as input and are evaluated using LLMs. They leverage the power of LLMs to answer new kinds of queries: W
arXiv:2605.10744v1 Announce Type: new Abstract: Safety-critical planning in complex environments, particularly at urban intersections, remains a fundamental challenge for autonomous driving. Existing
arXiv:2603.28902v2 Announce Type: replace Abstract: Charts are central to analytical reasoning, yet existing benchmarks for chart understanding focus almost exclusively on single-chart interpretation
arXiv:2605.10426v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have emerged as a promising paradigm for end-to-end autonomous driving. However, existing reasoning mechanisms sti
arXiv:2603.04737v2 Announce Type: replace Abstract: Existing reasoning evaluation paradigms suffer from different limitations: fixed benchmarks are increasingly saturated and vulnerable to contaminati
arXiv:2605.08646v1 Announce Type: cross Abstract: Large language model (LLM) agents face a structural tension: cloud agents provide strong reasoning but expose user data, while on-device agents preser
arXiv:2605.10218v1 Announce Type: new Abstract: Diffusion large language models (dLLMs) offer a promising route to parallel and efficient text generation, but improving their reasoning ability require
arXiv:2509.08461v3 Announce Type: replace-cross Abstract: Recent advances in Large Language Models (LLMs) have demonstrated their remarkable capacity to process and reason over structured and unstruct
arXiv:2605.06755v1 Announce Type: cross Abstract: Reinforcement learning is widely used to improve the reasoning ability of large language models, especially when answers can be automatically checked.
Executive Summary Since our February 2026 report on AI-related threat activity, Google Threat Intelligence Group (GTIG) has continued to track a maturing transition from nascent AI-enabled operations
arXiv:2509.26272v3 Announce Type: replace Abstract: The rapid rise of synthetic media has made deepfake detection a critical challenge for online safety and trust. Progress remains constrained by the
arXiv:2605.07725v1 Announce Type: cross Abstract: Tool-integrated reasoning (TIR) is difficult to scale to small language models due to instability in long-horizon tool interactions and limited model
arXiv:2602.14872v2 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) has been a main driver of recent breakthroughs in large reasoning models. Yet it remains a mys
arXiv:2605.03327v1 Announce Type: new Abstract: Reinforcement learning is crucial for aligning large language models to perform complex reasoning tasks. However, current algorithms such as Group Relat
arXiv:2505.20740v3 Announce Type: replace Abstract: The rapid advancement of multimodal large language models (MLLMs) offers new opportunities for complex scientific challenges, yet their application
arXiv:2605.01278v1 Announce Type: new Abstract: In this work, we present Valley3, an omni multimodal large language model (MLLM) developed for diverse global e-commerce tasks, with unified understandi
arXiv:2511.21678v2 Announce Type: replace-cross Abstract: MLLMs exhibit strong reasoning on isolated queries, yet they operate de novo -- solving each problem independently and often repeating the sam
arXiv:2601.13398v2 Announce Type: replace Abstract: LLMs demonstrate strong performance on code benchmarks, yet consistent reasoning across forward and backward execution remains elusive. We present R
arXiv:2605.02277v1 Announce Type: new Abstract: Factual Error Correction (FEC) aims to revise inaccurate text into statements that are factually consistent with external evidence. Although recent meth
arXiv:2605.02600v1 Announce Type: new Abstract: While Large Language Models (LLMs) and Vision-Language Models (VLMs) demonstrate remarkable capabilities in high-level reasoning and semantic understand
arXiv:2601.21714v2 Announce Type: replace Abstract: The evolution of Large Language Model (LLM) agents towards System~2 reasoning, characterized by deliberative, high-precision problem-solving, requir
arXiv:2605.01484v1 Announce Type: new Abstract: With the rapidly improving reasoning abilities of Large Language Models (LLMs), there is also a rising demand to use them in a wide variety of domains.
arXiv:2605.02130v1 Announce Type: new Abstract: Human-level agentic intelligence extends beyond low-level geometric perception, evolving from recognizing where things are to understanding what they ar
arXiv:2605.01520v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) frequently suffer from visual perception errors and hallucinations that compromise answer accuracy in complex reasoning
arXiv:2605.01823v1 Announce Type: new Abstract: Recently, Reinforcement Learning from Verifiable Rewards (RLVR) has been established as a highly effective technique for augmenting the math reasoning s
arXiv:2601.19827v3 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) extends large language models (LLMs) beyond parametric knowledge, yet it is unclear when iterative retrieval-re
arXiv:2604.27354v1 Announce Type: new Abstract: Explainable AI (XAI) aims to improve user understanding and decisions when using AI models. However, despite innovations in XAI, recent user evaluations
arXiv:2604.27540v1 Announce Type: new Abstract: Scientific reasoning rarely stops at what is directly observable; it often requires uncovering hidden structure from data. From estimating reaction cons
arXiv:2512.14044v3 Announce Type: replace-cross Abstract: The deployment of Vision-Language Models (VLMs) in safety-critical domains like autonomous driving (AD) is critically hindered by reliability
arXiv:2604.25259v1 Announce Type: new Abstract: Traffic signal control (TSC) plays a central role in reducing congestion and maintaining urban mobility. This dissertation introduces DGLight, a critic-
I just released LLM 0.32a0, an alpha release of my LLM Python library and CLI tool for accessing LLMs, with some consequential changes that I've been working towards for quite a while. Previous versio
arXiv:2510.18346v2 Announce Type: replace Abstract: Audio-Visual Question Answering (AVQA) requires models to effectively utilize both visual and auditory modalities to answer complex and diverse ques
arXiv:2602.02556v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are largely static and often redo reasoning or repeat mistakes. Prior experience reuse typically relies on extern
arXiv:2604.24647v1 Announce Type: cross Abstract: Long-context reasoning is a critical capability of large language models (LLMs), enabling applications such as long-document understanding, summarizat
arXiv:2512.03847v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has shown strong performance in LLM post-training, but real-world deployment often involves noisy or incomplete su
arXiv:2508.21094v3 Announce Type: replace Abstract: Video-LLMs face a fundamental tension in long-video reasoning: static, sparse frame sampling either dilutes evidence across task-irrelevant segments
arXiv:2604.23988v1 Announce Type: cross Abstract: Time series models predict numbers; decision-makers need advisory -- directional signals with reasoning, actionable suggestions, and risk management.
arXiv:2604.24583v1 Announce Type: new Abstract: Recent advancements in reinforcement learning with verifiable rewards (RLVR) have significantly improved the complex reasoning ability of vision-languag
arXiv:2506.11480v4 Announce Type: replace-cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a key technique for enhancing LLMs' reasoning abilities, yet its data ineffic
arXiv:2602.00981v2 Announce Type: replace-cross Abstract: Spoken question-answering (SQA) systems relying on automatic speech recognition (ASR) often struggle with accurately recognizing medical termi
arXiv:2604.22875v1 Announce Type: cross Abstract: When answering questions about images, humans naturally point, label, and draw to explain their reasoning. In contrast, modern vision-language models
arXiv:2604.24005v1 Announce Type: cross Abstract: On-policy distillation (OPD) has shown strong potential for transferring reasoning ability from frontier or domain-specific models to smaller students
arXiv:2604.22280v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have emerged as a promising foundation for universal multimodal embeddings. Recent studies have shown that reas
arXiv:2604.22306v1 Announce Type: cross Abstract: Large Language Models (LLMs) have demonstrated remarkable performance across a broad spectrum of tasks, including natural language understanding, dial
arXiv:2604.22498v1 Announce Type: cross Abstract: Although Multimodal Large Language Models (MLLMs) have advanced rapidly, they still face notable challenges in fine-grained multi-image understanding,
DeepSeek V4 models on Ollama Cloud support three thinking modes: 'No thinking' for fast answers, 'Thinking' for careful analysis, and 'Max thinking' for maximum reasoning effort . Users can adjust thi
arXiv:2604.22063v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly utilized in clinical reasoning and risk assessment. However, their interpretive reliability in critical
Google Cloud Next ‘26 took place this week in Las Vegas, and the energy was incredible as we welcomed over 32,000 leaders, developers, and partners to explore the Agentic Era with us. Across three key
arXiv:2604.21363v1 Announce Type: new Abstract: Bridging the gap between embodied intelligence and embedded deployment remains a key challenge in intelligent robotic systems, where perception, reasoni
arXiv:2604.05846v2 Announce Type: replace Abstract: Large Language Models (LLMs) increasingly rely on agentic capabilities-iterative retrieval, tool use, and decision-making-to overcome the limits of
arXiv:2604.21590v1 Announce Type: new Abstract: Modern industrial applications increasingly demand language models that act as agents, capable of multi-step reasoning and tool use in real-world settin
arXiv:2604.21354v1 Announce Type: new Abstract: Behavior sequences, composed of executable steps, serve as the operational foundation for multi-constraint planning problems such as travel planning. In