Knowledge catalogue
arXiv:2604.20140v1 Announce Type: new Abstract: Direct Preference Optimization (DPO) is an effective framework for aligning large language models with human preferences, but it struggles with complex
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: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
⚡️⚡️Run Qwen3.6-27B locally! @UnslothAI Qwen3.6-27B can now run locally! 💜 Run on 18GB RAM via Unsloth Dynamic GGUFs. Qwen3.6-27B surpasses Qwen3.5-397B-A17B on all major coding benchmarks. GGUFs: htt
arXiv:2604.19689v1 Announce Type: new Abstract: Understanding artworks requires multi-step reasoning over visual content and cultural, historical, and stylistic context. While recent multimodal large
arXiv:2603.13779v2 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) have achieved impressive success in natural visual understanding, yet they consistently underperform
arXiv:2604.19016v1 Announce Type: new Abstract: Cultural alignment in Large Language Models (LLMs) is essential for producing contextually aware, respectful, and trustworthy outputs. Without it, model
arXiv:2604.19395v1 Announce Type: new Abstract: While self-consistency is known to improve performance on symbolic reasoning, its effect on the recall of encyclopedic knowledge is unclear due to a lac
arXiv:2604.19259v1 Announce Type: new Abstract: Multi-class defect detection constitutes a critical yet challenging task in industrial quality inspection, where existing approaches typically suffer fr
arXiv:2604.18936v1 Announce Type: cross Abstract: Despite the growing application of Large Language Models (LLMs) to theoretical physics, there is little academic exploration into how domain-specific
LM Performance：With only 27B parameters, Qwen3.6-27B outperforms the Qwen3.5-397B-A17B (397B total / 17B active, ~15x larger!) on every major coding benchmark — including SWE-bench Verified (77.2 vs.
ml-intern by @huggingface is wild 🔥 You drop a high-level prompt (“build the best scientific reasoning model” or “crush healthcare benchmarks”) and this open-source agent does the entire post-training
arXiv:2604.05090v2 Announce Type: replace Abstract: Multilingual language models (LMs) organize representations for typologically and orthographically diverse languages into a shared parameter space,
arXiv:2604.19344v1 Announce Type: new Abstract: Robotic parkour provides a compelling benchmark for advancing locomotion over highly challenging terrain, including large discontinuities such as elevat
arXiv:2604.01375v2 Announce Type: replace Abstract: Rubric-based evaluation is widely used in LLM benchmarks and training pipelines for open-ended, less verifiable tasks. While prior work has demonstr
arXiv:2604.19633v1 Announce Type: new Abstract: Evaluating the reasoning capabilities of Large Language Models (LLMs) for complex, quantitative financial tasks is a critical and unsolved challenge. St
Today we’re introducing two big steps for health at OpenAI: - ChatGPT for Clinicians, a free version of ChatGPT designed for clinical work - HealthBench Professional, a new benchmark to evaluate real
arXiv:2604.19635v1 Announce Type: cross Abstract: While generative models have set new benchmarks for Target Speaker Extraction (TSE), their inherent reliance on global context precludes deployment in
arXiv:2604.19697v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have shown promising reasoning abilities, yet evaluating their performance in specialized domains remains chall
arXiv:2601.08620v2 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) pipelines must address challenges beyond simple single-document retrieval, such as interpreting visual elements
arXiv:2509.24478v2 Announce Type: replace Abstract: Modern neural networks have greatly improved performance across speech recognition benchmarks. However, gains are often driven by frequent words wit
arXiv:2604.17065v1 Announce Type: new Abstract: Human Activity Recognition (HAR) involves the automatic identification of user activities and has gained significant research interest due to its broad
arXiv:2604.17574v1 Announce Type: new Abstract: Distractor generation (DG) remains a labor-intensive task that still significantly depends on domain experts. The task focuses on generating plausible y
arXiv:2604.17927v1 Announce Type: new Abstract: Visual decoding of neurophysiological signals is a critical challenge for brain-computer interfaces (BCIs) and computational neuroscience. However, curr
arXiv:2604.17959v1 Announce Type: new Abstract: Expressive Human Pose and Shape Estimation (EHPS) plays a crucial role in various AR/VR applications and has witnessed significant progress in recent ye
arXiv:2604.18543v1 Announce Type: cross Abstract: Constructing environments for training and evaluating claw-like agents remains a manual, human-intensive process that does not scale. We argue that wh
arXiv:2604.17716v1 Announce Type: new Abstract: The validity screen (Cacioli, 2026d, 2026e) classifies LLM confidence signals as Valid, Indeterminate, or Invalid. We test whether these classifications
AES-128 remains secure against quantum computers and does not require key size changes as part of the post-quantum transition. NIST considers AES-128 safe and has made it the security benchmark for po
arXiv:2604.17718v1 Announce Type: new Abstract: Many benchmarks show that large language models can answer direct questions about culture. We study a different question: do they also change how they s
arXiv:2604.17841v1 Announce Type: new Abstract: Most autonomous driving safety benchmarks use time-to-collision (TTC) to assess risk and guide safe behaviour. However, TTC-based methods treat risk as
arXiv:2604.17194v1 Announce Type: cross Abstract: Converting betting odds into accurate outcome probabilities is a fundamental challenge in order to use betting odds as a benchmark for sports forecast
arXiv:2604.18547v1 Announce Type: cross Abstract: Verification of model outputs is rapidly emerging as a key primitive for both training and real-world deployment of large language models (LLMs). In p
Everyone heading into Google Cloud Next this week is bracing for another wave of artificial intelligence announcements. More Gemini. More agents. More benchmarks. More onstage demos that look great in
arXiv:2604.17870v1 Announce Type: new Abstract: Skill ecosystems for LLM agents have matured rapidly, yet recent benchmarks show that providing agents with more skills does not monotonically improve p
arXiv:2604.17745v1 Announce Type: new Abstract: Recent advances in large language models have highlighted their potential to automate computational research, particularly reproducing experimental resu
arXiv:2604.16320v1 Announce Type: cross Abstract: LLMs demonstrate remarkable reasoning capabilities, yet whether they utilize internal world models or rely on sophisticated pattern matching remains o
HUGGING FACE JUST AUTOMATED THEIR ENTIRE POST-TRAINING TEAM WITH AN AGENT. It reads papers, runs GPU experiments, iterates, and builds research-backed models autonomously. Pushed a benchmark from 10%
arXiv:2604.16747v1 Announce Type: new Abstract: Dynamic 3D Gaussian Splatting methods achieve strong training-view PSNR on monocular video but generalize poorly: on the D-NeRF benchmark we measure an
arXiv:2505.16522v3 Announce Type: replace Abstract: With the evolution of large language models (LLMs), their robustness against individual simple biases has been enhanced. However, we observe that th
arXiv:2604.17886v1 Announce Type: new Abstract: Users often omit essential details in their requests to LLM-based agents, resulting in under-specified inputs for tool use. This poses a fundamental cha
arXiv:2604.17862v1 Announce Type: new Abstract: As deep learning-based AI technologies gain momentum, the demand for general-purpose AI computing architectures continues to grow. While GPGPU-based arc
arXiv:2601.09853v2 Announce Type: replace Abstract: Real-world health questions from patients often unintentionally embed false assumptions or premises. In such cases, safe medical communication typic
arXiv:2603.02618v3 Announce Type: replace Abstract: Out-of-distribution (OOD) detection seeks to identify samples from unknown classes, a critical capability for deploying machine learning models in o
arXiv:2604.18347v1 Announce Type: new Abstract: Vision Language Models (VLMs) achieved rapid progress in the recent years. However, despite their growth, VLMs development is heavily grounded on Englis
arXiv:2604.18105v1 Announce Type: cross Abstract: Integrating large language models (LLMs) into automatic speech recognition (ASR) has become a mainstream paradigm in recent years. Although existing L
arXiv:2602.06663v2 Announce Type: replace Abstract: Unified multimodal models (UMMs) have shown impressive capabilities in generating natural images and supporting multimodal reasoning. However, their
QIMMA (قِمّة) is a quality-focused leaderboard for evaluating Arabic Large Language Models, developed by TIIUAE. The leaderboard benchmarks Arabic LLMs across various performance metrics and tasks to
arXiv:2411.15115v3 Announce Type: replace-cross Abstract: Recent text-to-video (T2V) diffusion models have made remarkable progress in generating high-quality videos. However, they often struggle to a
arXiv:2508.15815v3 Announce Type: replace Abstract: Modern large language models (LLMs) are typically trained and deployed using structured role tags (e.g. system, user, assistant, tool) that explicit
arXiv:2402.13243v2 Announce Type: replace Abstract: Learning a human-like driving policy from large-scale driving demonstrations is promising, but the uncertainty and non-deterministic nature of plann
arXiv:2604.15708v1 Announce Type: new Abstract: The advent of deep neural networks has led to remarkable progress in 3D point cloud recognition, but they remain vulnerable to adversarial attacks. Alth
arXiv:2604.16158v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly rely on chain-of-thought (CoT) reasoning to solve complex tasks. Yet ensuring that the reasoning trace both
arXiv:2604.15808v1 Announce Type: cross Abstract: Spatial reasoning and visual grounding are core capabilities for vision-language models (VLMs), yet most medical VLMs produce predictions without tran
arXiv:2604.15573v1 Announce Type: cross Abstract: In recent years, neural networks and other complex models have dominated recommender systems, often setting new benchmarks for state-of-the-art perfor
arXiv:2604.15555v1 Announce Type: new Abstract: Chest X-ray (CXR) interpretation is hindered by the long-tailed distribution of pathologies and the open-world nature of clinical environments. Existing
arXiv:2509.09530v2 Announce Type: replace Abstract: Three-dimensional ultrasound (US) offers many clinical advantages over conventional 2D imaging, yet its widespread adoption is limited by the cost a
arXiv:2604.15961v1 Announce Type: new Abstract: There is no consensus in the field of synthetic data on concise metrics for quality evaluations or benchmarks on large health datasets, such as historic
arXiv:2604.15388v1 Announce Type: cross Abstract: Recent advances in large language models have improved code generation, but their use in hardware description languages is still limited. Moreover, tr
arXiv:2602.01566v2 Announce Type: replace Abstract: Deep research is emerging as a representative long-horizon task for large language model (LLM) agents. However, long trajectories in deep research o
life when you discover an open-source model that runs 300 parallel agents, executes for 12+ hours straight, beats GPT-5.4 and opus 4.6 on multiple benchmarks... and the weights are on huggingface Medi