Knowledge catalogue
arXiv:2605.22068v1 Announce Type: new Abstract: We formalize and enable the task of open tree decomposition, which segments an image into hierarchical trees of visual components with unconstrained gra
arXiv:2506.11060v2 Announce Type: replace-cross Abstract: Large Language Model (LLM)-based coding agents have shown promising results on coding benchmarks, but their effectiveness on systems code rema
arXiv:2605.22447v1 Announce Type: new Abstract: The study of online discourse has become central to understanding societal polarization. While much research has focused on detecting overt toxicity, th
arXiv:2605.21845v1 Announce Type: new Abstract: Suicide is a leading cause of death in the United States, and understanding the circumstances that precede it requires extracting structured information
arXiv:2605.22082v1 Announce Type: new Abstract: We present CoRMA(Contrastive Robotic Motor Adaptation), a context-based meta-adaptation framework that modifies RMA for force-dominant assembly. CoRMA r
arXiv:2605.22137v1 Announce Type: new Abstract: Although Large Language Models (LLMs) demonstrate strong capabilities across various tasks, they exhibit significant performance discrepancies across la
arXiv:2605.21854v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have rapidly converged on a small set of architectural patterns: discrete-token autoregression (e.g. OpenVLA) and co
arXiv:2602.08023v3 Announce Type: replace-cross Abstract: Existing benchmarks for LLM-based offensive security agents use isolated, single-target setups with a known vulnerable service and fixed objec
Cursor Composer 2.5's is 3–18x cheaper than Opus 4.7 in Claude Code (medium reasoning), and 5–32x cheaper than GPT-5.5 in Codex (medium) based on API pricing This low Cost per Task isn't just driven b
arXiv:2605.20690v1 Announce Type: new Abstract: Agentic discovery has shown that LLM-driven search can find novel algorithms, designs, and code under benchmark conditions. Translating the paradigm to
After 15 months of incremental updates, leaks, and rumored leaks, DeepSeek released version 4. It arrived without the fanfare R1 and R1-preview commanded in early 2025. That quiet reception is the mos
DeepSeek released two advanced AI models—R1 and V3—with R1 specializing in complex reasoning and V3 designed for large-scale language processing. Notably, DeepSeek developed these high-performing mode
arXiv:2605.21482v1 Announce Type: new Abstract: Deep research, in which an agent searches the open web, collects evidence, and derives an answer through extended reasoning, is a prominent use case for
arXiv:2509.20912v4 Announce Type: replace Abstract: Recent advances in multimodal language models (MLLMs) have made thinking with images a dominant paradigm for multimodal reasoning. However, existing
arXiv:2510.08759v2 Announce Type: replace Abstract: Understanding the capability bottlenecks of embodied multimodal large language models (MLLMs) is crucial for improving embodied agents. However, exi
arXiv:2605.22017v1 Announce Type: new Abstract: Deepgenerative models havebecomeapromisingapproach for human motion prediction due to their ability to capture multimodal distributions and represent di
arXiv:1709.03806v2 Announce Type: replace Abstract: Modern vision models have achieved strong object-recognition performance, yet it remains unclear whether their representations encode object-level s
arXiv:2605.21827v1 Announce Type: new Abstract: Do language models preserve the ordinal meaning of intensity words when those words must produce numeric actions? I study a researcher-constructed scale
arXiv:2605.21964v1 Announce Type: new Abstract: Computational imaging enables compact infrared systems, but deep-learning pipelines that combine image reconstruction and object detection often introdu
arXiv:2605.22138v1 Announce Type: cross Abstract: How should an agent decide when and how to plan? A dominant approach builds agents as reactive policies with adaptive computation (e.g., chain-of-thou
Essential context on OpenAI’s Erdos result I truly miss the age of science and transparency in AI. Especially given how much money and political power and governance and scientific understanding is at
arXiv:2503.17599v3 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated considerable potential in general practice. However, existing benchmarks and evaluation frameworks pr
arXiv:2605.22785v1 Announce Type: new Abstract: AI chatbots are rapidly shaping how people encounter the news, yet no prior study has systematically measured how accurately these systems, with their p
arXiv:2605.20630v1 Announce Type: new Abstract: Industrial asset operations workflows are latency-sensitive because a single user query may require coordination over sensor data, work orders, failure
arXiv:2605.22186v1 Announce Type: new Abstract: Event-based low-light image enhancement (LIE) methods mainly focus on incorporating high dynamic range (HDR) information from events while overlooking t
arXiv:2605.22139v1 Announce Type: new Abstract: Gait recognition enables non-intrusive, privacy-preserving identification but suffers in uncontrolled environments due to illumination and motion sensit
arXiv:2605.22552v1 Announce Type: new Abstract: Fashion image retrieval is a cornerstone of modern e-commerce systems. A unified framework that supports diverse query formats and search intentions is
arXiv:2605.21625v1 Announce Type: cross Abstract: The emergence of Large Vision-Language Models (LVLMs) has significantly advanced video understanding capabilities. However, existing benchmarks focus
arXiv:2605.22018v1 Announce Type: new Abstract: The Flooded Road Environments Dataset (FRED) is, to our knowledge, the first multi-modal autonomous driving dataset specifically targeting the collectio
arXiv:2605.21558v1 Announce Type: cross Abstract: Adapting Large Language Models (LLMs) to specialized domains typically incurs high data and computational overhead. While prior efficiency efforts hav
arXiv:2605.22413v1 Announce Type: new Abstract: Extracting structured information from visual documents (Visual Information Extraction, VIE) is a cornerstone of business automation. While recent Multi
Gemini Flash 3.5 is such a disappointing model. It's intelligence and speed is awesome. Absolutely amazing. But it's been trained to max evals, not to be helpful to humans. It goes off and does random
arXiv:2605.22558v1 Announce Type: new Abstract: Spatio-temporal reasoning in vision-language models requires visual representations that preserve physical geometry rather than merely semantic appearan
arXiv:2605.22228v1 Announce Type: new Abstract: Aspect-based sentiment analysis (ABSA) requires models to bind sentiment evidence to the correct aspect, making it a natural testbed for fine-grained st
Jeremy Howard comments on comparative performance trends between GPT 5.5 and Claude models, noting that GPT 5.5 appears to be improving in a particular capability while Claude models are declining in
arXiv:2605.20203v1 Announce Type: cross Abstract: As older adults increasingly use LLM-based chatbots for companionship and assistance, a safety gap is emerging. Older adults may face vulnerabilities
arXiv:2605.22629v1 Announce Type: new Abstract: Parametric human models capture global pose but cannot represent the non-rigid surface dynamics of clothing and soft tissue. Generic scene flow estimate
ha ha, so much for step change? maybe this problem was just easier than some? The standard GPT-5.5 reproduced the proof ~ 👇 https://chatgpt.com/share/6a0e9e04-8cb0-8332-a4f1-ec68acd2e03e You don't nee
arXiv:2605.22007v1 Announce Type: new Abstract: Hallucination is often viewed as a direct consequence of missing knowledge: a model answers incorrectly when the correct answer is absent from its gener
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
Highlighting the new WebGPU backend in llama.cpp/ggml The work to bring full-fledged WebGPU support in llama.cpp started about an year and a half ago. It has been lead by @reeselevine and team at USCS
Highlights from today’s Codex Thursday launches: 1️⃣ Codex can now securely use apps on your Mac from your phone, even when your Mac is locked and the screen is off. http://developers.openai.com/codex
Virgin Atlantic implemented OpenAI's Codex to accelerate software development and deployment processes, enabling faster shipping of features and updates. The case study demonstrates how Codex improved
arXiv:2602.01851v2 Announce Type: replace Abstract: Recent generative models have achieved remarkable progress in image editing. However, existing systems and benchmarks remain largely text-guided. In
arXiv:2605.22064v1 Announce Type: new Abstract: Hy-MT2 is a family of fast-thinking multilingual translation models designed for complex real-world scenarios. It includes three model sizes: 1.8B, 7B,
arXiv:2605.22035v1 Announce Type: cross Abstract: Continual Visual Question Answering (VQA) requires learning from non-stationary streams of visual inputs and questions while preserving past knowledge
I have to eat crow on this, in light of further information. whatever OpenAI spent on Erdos using a new model, apparently you can get GPT 5.5 to do something similar; @emollick’s presumably estimates
I think people don't realize why Gemini Omni is different than other video AIs. It is fully multimodal, so it can edit video natively, too I took the famous 'train ' movie from 1896 & made it a bullet
I truly miss the age of science and transparency in AI. Especially given how much money and political power and governance and scientific understanding is at stake. We don’t know for example • How man
arXiv:2605.22247v1 Announce Type: new Abstract: Idioms pose a fundamental challenge for language models, as their meaning cannot be inferred from surface form alone. Understanding such expressions, th
arXiv:2510.00948v2 Announce Type: replace Abstract: Real-world videos often extend over thousands of frames. Existing generative video super-resolution (VSR) approaches, however, face two persistent c
arXiv:2602.23200v2 Announce Type: replace-cross Abstract: When transformer-based language models are deployed for text generation, most of the inference time is spent in the decoding stage, where outp
arXiv:2510.09724v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly capable of generating complete applications from natural language instructions, creating new opp
Introducing Qwen3.7-Max from @Alibaba_Qwen, Qwen’s flagship model for the agent era with 1M context and leading performance across agentic coding, reasoning, and long-horizon autonomy. AI natives can
arXiv:2605.22079v1 Announce Type: new Abstract: Large language models (LLMs) are widely used to generate structured outputs such as JSON, SQL, and code, yet public resources remain limited for evaluat
arXiv:2605.22080v1 Announce Type: new Abstract: We introduce JMed48k, a multi-profession Japanese healthcare licensing benchmark for evaluating vision-language models. Built from official PDF material
arXiv:2605.21861v1 Announce Type: new Abstract: Multi-modality medical vision (MV) foundation models (FM) are fundamentally challenged by pronounced Non-IID feature statistics across heterogeneous ima
arXiv:2605.21988v1 Announce Type: new Abstract: Video large language models (Video LLMs) achieve strong benchmark accuracy, yet often answer video questions through shortcuts such as single-frame cues
arXiv:2605.21573v1 Announce Type: new Abstract: We introduce Lens, a 3.8B-parameter T2I model that achieves performance competitive with, and in several cases surpassing, state-of-the-art models with
arXiv:2601.04537v3 Announce Type: replace-cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has driven significant performance gains in reasoning-oriented large language models (LL