Kimi K2.6 becomes the #1 open model on MathArena!
Kimi K2.6 achieved the top ranking on MathArena, a benchmark for evaluating mathematical problem-solving capabilities in open-source language models. This announcement highlights the model's superior
Knowledge catalogue
Kimi K2.6 achieved the top ranking on MathArena, a benchmark for evaluating mathematical problem-solving capabilities in open-source language models. This announcement highlights the model's superior
arXiv:2502.12911v3 Announce Type: replace Abstract: Generating SQLs from user queries is a long-standing challenge, where the accuracy of initial schema linking significantly impacts subsequent SQL ge
arXiv:2604.20487v1 Announce Type: cross Abstract: Large language models (LLMs) encode knowledge in parametric weights, making it costly to update or extend without retraining. Retrieval-augmented gene
arXiv:2604.19782v1 Announce Type: cross Abstract: Recent advances in large audio language models (LALMs) have enabled multilingual speech understanding. However, benchmarks for evaluating LALMs remain
arXiv:2601.13240v2 Announce Type: replace-cross Abstract: Large language models (LLMs) excel at general programming but struggle with domain-specific software development, necessitating domain special
arXiv:2604.19815v1 Announce Type: new Abstract: Drug repurposing is often framed as a candidate identification task, but existing approaches provide limited guidance for distinguishing biologically pl
arXiv:2604.20652v1 Announce Type: new Abstract: Large language models trained on human feedback may suppress fraud warnings when investors arrive already persuaded of a fraudulent opportunity. We test
Last night was the biggest disaster in the history of Tesla. Let me walk you through what actually happened on that earnings call, because the headlines are doing you a disservice: Elon Musk got on th
Last week, we launched Gemini 3.1 TTS, our latest and best text-to-speech model. This new model introduces [awe] audio tags, an intuitive way to guide vocal style, pace, and delivery. Here are some ti
arXiv:2506.02276v2 Announce Type: replace Abstract: Stochastic Interpolants (SI) is a powerful framework for generative modeling, capable of flexibly transforming between two probability distributions
arXiv:2604.20556v1 Announce Type: cross Abstract: Currently, Large Language Models (LLMs) feature a diversified architectural landscape, including traditional Transformer, GateDeltaNet, and Mamba. How
arXiv:2604.20714v1 Announce Type: new Abstract: Designing and optimizing multi-agent systems (MAS) is a complex, labor-intensive process of 'Agent Engineering.' Existing automatic optimization methods
arXiv:2604.19895v1 Announce Type: new Abstract: A well-known limitation of AI systems is presumptuousness: the tendency of AI systems to provide confident answers when information may be lacking. This
arXiv:2604.20090v1 Announce Type: new Abstract: Cross-lingual chain-of-thought (XCoT) with self-consistency markedly enhances multilingual reasoning, yet existing methods remain costly due to extensiv
arXiv:2604.17931v2 Announce Type: replace Abstract: Reinforcement Learning (RL) has emerged as a powerful training paradigm for LLM-based agents. However, scaling agentic RL for deep research remains
arXiv:2501.03624v2 Announce Type: replace-cross Abstract: Large language models (LLMs) excel on many NLP benchmarks, but their behavior on real-world, semi-structured prediction remains underexplored.
arXiv:2604.20304v1 Announce Type: cross Abstract: Constructing phase diagrams for multicomponent alloys requires extensive experimental measurements and is a time-consuming task. Here we investigate w
looks like new Pareto frontiers across everything: - Context: 400K context in Codex and a 1M in API - API Pricing: 5/m input and 30/m output tokens. - Codex improved its own inference speed 20% lol -
arXiv:2308.03303v2 Announce Type: replace Abstract: Fine-tuning large language models (LLMs) is crucial for improving their performance on downstream tasks, but full-parameter fine-tuning (Full-FT) is
arXiv:2604.20286v1 Announce Type: cross Abstract: Recent segmentation models have demonstrated promising efficiency by aggressively reducing parameter counts and computational complexity. However, the
arXiv:2604.20650v1 Announce Type: new Abstract: 6D object pose estimation in cluttered scenes remains challenging due to severe occlusion and sensor noise. We propose MAPRPose, a two-stage framework t
arXiv:2604.20545v1 Announce Type: new Abstract: In measurement theory, instruments do not simply record reality; they help constitute what is observed. The same holds for generative AI evaluation: ben
arXiv:2604.20148v1 Announce Type: cross Abstract: Can small language models achieve strong tool-use performance without complex adaptation mechanisms? This paper investigates this question through Met
arXiv:2601.11505v2 Announce Type: replace-cross Abstract: Progress in Type 1 Diabetes (T1D) algorithm development is limited by the fragmentation and lack of standardization across existing T1D manage
Microsoft is rolling out a new Agent Mode inside Office apps like Word, Excel, and PowerPoint this week. Previously described by Microsoft as 'vibe working,' the Agent Mode is a more powerful version
arXiv:2604.19809v1 Announce Type: new Abstract: We introduce MIRROR, a benchmark comprising eight experiments across four metacognitive levels that evaluates whether large language models can use self
arXiv:2604.14785v2 Announce Type: replace Abstract: Recent progress in Multimodal Large Language Models (MLLMs) has demonstrated remarkable advances in perception and reasoning, suggesting their poten
arXiv:2604.20366v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) exhibit powerful generative capabilities but frequently produce hallucinations that compromise output reliability.
arXiv:2604.16756v2 Announce Type: replace-cross Abstract: Prompt-induced cognitive biases are changes in a general-purpose AI (GPAI) system's decisions caused solely by biased wording in the input (e.
arXiv:2412.14590v2 Announce Type: replace Abstract: Quantization has become one of the most effective methodologies to compress LLMs into smaller size. However, the existing quantization solutions sti
arXiv:2604.20393v1 Announce Type: new Abstract: With the development of deep learning, ViT-based stereo matching methods have made significant progress due to their remarkable robustness and zero-shot
arXiv:2604.19811v1 Announce Type: cross Abstract: AI leaders and safety reports increasingly warn that advances in model reasoning may enable biological misuse, including by low-expertise users, while
arXiv:2505.18823v2 Announce Type: replace Abstract: Accurate medical image segmentation allows for the precise delineation of anatomical structures and pathological regions, which is essential for tre
arXiv:2604.20496v1 Announce Type: cross Abstract: The April 2026 Claude Mythos sandbox escape exposed a critical weakness in frontier AI containment: the infrastructure surrounding advanced models rem
The Codex app now includes several new features: GPT-5.5 integration, browser control capabilities, support for Google Sheets and Slides, document and PDF handling, OS-wide dictation functionality, an
arXiv:2601.19932v2 Announce Type: replace Abstract: Coded language is an important part of human communication. It refers to cases where users intentionally encode meaning so that the surface text dif
arXiv:2604.20806v1 Announce Type: cross Abstract: Large vision-language models (LVLMs) have made substantial advances in reasoning tasks at the Olympiad level. Nevertheless, current Olympiad-level mul
arXiv:2604.20551v1 Announce Type: cross Abstract: Mixture-of-experts models provide a flexible framework for learning complex probabilistic input-output relationships by combining multiple expert mode
One day while testing GPT-5.5, I had my first taste of AGI. We had a branch with hundreds of visual and front-end changes, plus complex refactors. At the same time, main had changed a lot too. Conflic
Moonshot's Kimi AI demonstrated capabilities to generate comprehensive business reports from a single prompt, including a 100-page PDF with citations, a 30-page executive PowerPoint presentation, and
arXiv:2604.20719v1 Announce Type: cross Abstract: Omnimodal Notation Processing (ONP) represents a unique frontier for omnimodal AI due to the rigorous, multi-dimensional alignment required across aud
🚨 OpenAI just launched GPT-5.5. The OpenAI team was nice enough to give me early access over the last several weeks, and I just want to flag: there is a certain class of models (one that we’re hitting
Rachel Metz / Bloomberg: OpenAI launches GPT-5.5, designed to handle complex tasks with minimal guidance; the model will be used to power the company's upcoming “super app” — OpenAI is introducing an
OpenAI Group PBC today launched a new large language model that is significantly better than its predecessors at solving math problems and writing code. GPT-5.5 is rolling out a week after rival Anthr
OpenAI: OpenAI says “GPT-5.5 matches GPT-5.4 per-token latency in real-world serving, while performing at a much higher level of intelligence” — A new class of intelligence for real work — We're relea
Madison Mills / Axios: OpenAI says GPT-5.5's improvements are strongest in agentic coding, computer use, and early scientific research, which require reasoning across longer contexts — OpenAI on Thurs
OpenAI just announced its new GPT-5.5 model, which the company calls its 'smartest and most intuitive to use model yet, and the next step toward a new way of getting work done on a computer.' OpenAI j
AI agents have revolutionized developer workflows, and their next frontier is knowledge work: processing information, solving complex problems, coming up with new ideas and driving innovation. Codex,
arXiv:2506.20904v2 Announce Type: replace Abstract: We study offline reinforcement learning in average-reward MDPs, which presents increased challenges from the perspectives of distribution shift and
arXiv:2604.19832v1 Announce Type: cross Abstract: In a global derivatives market with notional values in the hundreds of trillions of dollars, the accuracy and efficiency of pricing models are of fund
Our own team was trying to figure out how to get LiteParse working in the browser 😂 Shouldn't have doubted Claude. Claude knows best. LiteParse is really neat! It does a great job of extracting text f
Over the past month, some of you reported Claude Code's quality had slipped. We investigated, and published a post-mortem on the three issues we found. All are fixed in v2.1.116+ and we’ve reset usage
arXiv:2604.20423v1 Announce Type: new Abstract: The rapid iteration of autonomous driving algorithms has created a growing demand for high-fidelity, replayable, and diagnosable testing data. However,
arXiv:2604.20835v1 Announce Type: new Abstract: Modern language models demonstrate impressive coding capabilities in common programming languages (PLs), such as C++ and Python, but their performance i
ParseBench is now live on @Kaggle. The first document OCR benchmark built for AI agents — 2,000 enterprise pages, 167K+ test rules, 5 dimensions that actually break downstream agents. Benchmark your p
arXiv:2604.19784v1 Announce Type: cross Abstract: Recently, it has been found that frontier AI models can resist their own shutdown, a behavior known as self-preservation. We extend this concept to th
arXiv:2602.07044v2 Announce Type: replace-cross Abstract: Pipeline integrity is critical to industrial safety and environmental protection, with Magnetic Flux Leakage (MFL) detection being a primary n
arXiv:2603.21373v2 Announce Type: replace-cross Abstract: In-context learning (ICL) adapts large language models by conditioning on a small set of ICL examples, avoiding costly parameter updates. Amon
arXiv:2604.20834v1 Announce Type: new Abstract: Recent advances in Vision-Language-Action (VLA) models have opened new avenues for robot manipulation, yet existing methods exhibit limited efficiency a
Generative artificial intelligence security startup Portal26 Inc. today announced the launch of a new module designed to rein in runaway token consumption by autonomous AI agents, a problem the compan