Search: “benchmark”

In an April 9, 2026 Substack post, AI skeptic Gary Marcus argues that Anthropic's announcement of its Claude 'Mythos' model was significantly overhyped, offering three key reasons for skepticism: t...

arXiv:2604.08541v1 Announce Type: cross Abstract: Multimodal Mixture-of-Experts (MoE) models have achieved remarkable performance on vision-language tasks. However, we identify a puzzling phenomenon t

arXiv:2604.08299v1 Announce Type: new Abstract: Chain-of-Thought (CoT) has become a cornerstone of reasoning in large language models, yet its effectiveness is constrained by the limited expressivenes

arXiv:2604.08532v1 Announce Type: new Abstract: Large-scale multi-view reconstruction models have made remarkable progress, but most existing approaches still rely on fully supervised training with gr

arXiv:2604.06389v1 Announce Type: new Abstract: Uncertainty estimation for reasoning language models remains difficult to deploy in practice: sampling-based methods are computationally expensive, whil

arXiv:2604.07766v1 Announce Type: new Abstract: We investigate a fundamental structural question in Grouped Query Attention (GQA) transformers: do the layers most sensitive to task correctness coincid

arXiv:2604.06636v1 Announce Type: cross Abstract: Process supervision has emerged as a promising approach for enhancing LLM reasoning, yet existing methods fail to distinguish meaningful progress from

arXiv:2601.23155v2 Announce Type: replace-cross Abstract: Information-based data selection for instruction tuning is compelling: maximizing the log-determinant of the Fisher information yields a monot

arXiv:2604.07725v1 Announce Type: cross Abstract: We show that verifier-free evolution is bottlenecked by both diversity and efficiency: without external correction, repeated evolution accelerates col

arXiv:2604.03647v2 Announce Type: replace-cross Abstract: In the unsupervised self-evolution of Multimodal Large Language Models, the quality of feedback signals during post-training is pivotal for st

arXiv:2603.04759v2 Announce Type: replace Abstract: The limited context window of contemporary large language models (LLMs) remains a primary bottleneck for their broader application across diverse do

arXiv:2603.11394v2 Announce Type: replace Abstract: Patients and clinicians are increasingly using chatbots powered by large language models (LLMs) for healthcare inquiries. While state-of-the-art LLM

arXiv:2604.07415v1 Announce Type: cross Abstract: Large language models (LLMs) are probabilistic in nature and perform more reliably when augmented with external information. As complex queries often

arXiv:2604.08370v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) has demonstrated impressive performance in 3D scene reconstruction. Beyond novel view synthesis, it shows great potential f

arXiv:2010.00638v2 Announce Type: replace-cross Abstract: Generative models for tabular data have evolved rapidly beyond Generative Adversarial Networks (GANs). While GANs pioneered synthetic tabular

arXiv:2604.07916v1 Announce Type: new Abstract: Referring Expression Segmentation (RES) aims to segment image regions described by natural-language expressions, serving as a bridge between vision and

arXiv:2604.08072v1 Announce Type: new Abstract: Convolutional Neural Networks (CNNs) excel at extracting local features hierarchically, but their performance in capturing complex correlations hinges h

arXiv:2604.06613v2 Announce Type: cross Abstract: Modern reasoning models continue generating long after the answer is already determined. Across five model configurations, two families, and three ben

arXiv:2604.06689v1 Announce Type: new Abstract: Accurate classification requires not only high predictive accuracy but also well-calibrated confidence estimates. Yet, modern deep neural networks (DNNs

arXiv:2512.08410v2 Announce Type: replace Abstract: Due to excessive memory overhead, most Multimodal Large Language Models (MLLMs) can only process videos of limited frames. In this paper, we propose

arXiv:2604.06831v1 Announce Type: cross Abstract: Current LLM-based services typically require users to submit raw text regardless of its sensitivity. While intuitive, such practice introduces substan

arXiv:2604.08156v1 Announce Type: new Abstract: Rhyme is deceptively intuitive: what is or is not a rhyme is constructed historically, scholars struggle with rhyme classification, and people disagree

arXiv:2511.19693v3 Announce Type: replace-cross Abstract: Payment networks form the backbone of modern commerce, generating high volumes of transaction records from daily activities. Properly modeling

arXiv:2604.07894v1 Announce Type: new Abstract: Personalized large language models (PLLMs) have garnered significant attention for their ability to align outputs with individual's needs and preference

arXiv:2507.22025v4 Announce Type: replace Abstract: The emergence of Multimodal Large Language Models (MLLMs) has driven significant advances in Graphical User Interface (GUI) agent capabilities. Neve

arXiv:2604.06214v1 Announce Type: cross Abstract: Efficient classification of surgical procedures by urgency is paramount to optimize patient care and resource allocation within healthcare systems. Th

arXiv:2604.06728v1 Announce Type: cross Abstract: Multimodal sarcasm detection (MSD) aims to identify sarcastic intent from semantic incongruity between text and image. Although recent methods have im

arXiv:2604.07264v1 Announce Type: cross Abstract: Operating LEO mega-constellations requires translating high-level operator intents ('reroute financial traffic away from polar links under 80 ms') int

arXiv:2604.06896v1 Announce Type: new Abstract: Epithelial tissues dynamically reshape through local mechanical interactions among cells, a process well captured by vertex models. Yet their many tunab

arXiv:2509.08016v2 Announce Type: replace Abstract: Video Large Language Models (VideoLLMs) face a critical bottleneck: increasing the number of input frames to capture fine-grained temporal detail le

We had Lin on stage: 'the future is millions of models — one per application, one per use case.' Jet delivered a masterclass on reinforcement fine-tuning. Rob joined @WorkOS for some hot takes on the

arXiv:2604.06558v1 Announce Type: new Abstract: We present the first systematic study of when target context helps molecular property prediction, evaluating context conditioning across 10 diverse prot

arXiv:2510.26241v5 Announce Type: replace-cross Abstract: Modern vision-language models (VLMs) excel at many multimodal tasks, yet their grasp of temporal information in video remains weak and has not

arXiv:2603.28906v2 Announce Type: replace Abstract: AGI has become the Holly Grail of AI with the promise of level intelligence and the major Tech companies around the world are investing unprecedente

arXiv:2602.22251v3 Announce Type: replace-cross Abstract: General-purpose 3D chemical modeling encompasses molecules and materials, requiring both generative and predictive capabilities. However, most

After playing with it a bit, Meta's Muse Spark Thinking is fine so far, but really doesn't match the current Big Three models. It also is a bit... weird. Like some strange language & tone, a little lo

The *Interconnects.ai* article argues that fears around releasing an open-weight version of Claude Mythos are overstated, noting that closed frontier models still lead open-weight ones in robust, ...

extremely fun jamming with Harrison on all things analytics, agents and evals! I have like 20 more hours worth of takes and opinions in this space and going on the pod uncorked them, more to come for

FlowInOne is a vision-centric multimodal image generation framework that reformulates multimodal generation as a purely visual flow, converting all inputs into visual prompts and enabling a clean i...

Google's Gemma 4 31B is a dense multimodal model from Google DeepMind now available on Together AI's serverless infrastructure via the endpoint `google/gemma-4-31B-it`. It features a 256K context ...

Grok is the AI to use if you value truth Grok 4.20 Non-Hallucination rate improved to even higher than previous highest Just days ago, it hit a record-breaking 78% Non-Hallucination Rate - already #1

Meh on the Lem Test as well https://x.com/emollick/status/2019478314767835634?s=20 Opus 4.6 saturates my Lem test, which I've done since GPT-3.5 SciFi author Stanislaw Lem wrote of two rival construct

NVIDIA's open-source project **Slinky** (developed by SchedMD, now part of NVIDIA) enables organizations to run full Slurm clusters directly on Kubernetes infrastructure by managing the complete li...

So we now have a pretty good picture of the state of the frontier AI model makers. US closed source models continue to lead. Google, OpenAI, and Anthropic stand well ahead of the pack, and may have si

ALTK-Evolve, published by IBM Research, is a memory system for AI agents that enables on-the-job learning by helping agents improve over time, learning from and using guidelines generated from pre...

Anthropic investigated the internal mechanisms of its latest unreleased model, Claude Mythos Preview, and what they found is 100% worth a read. Key things I pulled from Anthropic researchers' threads: