Search: “model-releases”

arXiv:2602.08404v2 Announce Type: replace Abstract: Diffusion large language models (dLLMs) have recently gained significant attention due to their inherent support for parallel decoding. Building on

arXiv:2605.22842v1 Announce Type: cross Abstract: Multi-agent AI pipelines typically assume that agent misconduct originates from model misalignment. We identify a structural failure in this assumptio

arXiv:2605.22870v1 Announce Type: cross Abstract: Chain-of-thought (CoT) prompting is necessary for arithmetic in small language models, yet shuffling its steps preserves most performance. What does C

arXiv:2601.21306v2 Announce Type: replace-cross Abstract: This paper investigates search in model-based reinforcement learning (RL). Conventional wisdom holds that long-term predictions and compoundin

arXiv:2605.22902v1 Announce Type: cross Abstract: Generative Vision-Language Models (VLMs) perform well on multimodal reasoning, but how visual inputs are transformed to text remains poorly understood

arXiv:2605.23171v1 Announce Type: cross Abstract: Recent advancements in instructional fine-tuning have injected noise into embeddings, with NEFTune (Jain et al., 2024) setting benchmarks using unifor

arXiv:2605.23464v1 Announce Type: new Abstract: We consider a decentralized setup in which the participants collaboratively train and serve a large neural network, and where each participant only proc

arXiv:2506.00560v2 Announce Type: replace-cross Abstract: End-to-end planning systems for autonomous driving are rapidly improving, especially in closed-loop simulation environments like CARLA. Many s

arXiv:2605.23381v1 Announce Type: new Abstract: Though rectified flow models have achieved remarkable performance in image, video, and 3D generation, their practical deployments are challenged by slow

arXiv:2407.04573v4 Announce Type: replace-cross Abstract: Dense vector retrieval is an important building block of modern machine learning systems, underlying applications ranging from semantic search

arXiv:2605.22907v1 Announce Type: new Abstract: Real-world long video understanding requires models to perform continuous tracking, information integration and memory retention over massive temporal s

arXiv:2602.07801v4 Announce Type: replace-cross Abstract: In long-video understanding, conventional uniform frame sampling often fails to capture key visual evidence, leading to degraded performance a

arXiv:2605.23518v1 Announce Type: new Abstract: Directly editing ultra-high-resolution (UHR) images is valuable but underexplored, primarily due to the lack of high-quality data and the challenge in m

arXiv:2605.23141v1 Announce Type: new Abstract: A useful test of visual concept learning is not just whether a model can recognize a concept in a single image, but whether it can preserve and manipula

arXiv:2605.23410v1 Announce Type: cross Abstract: The explosive growth of open-source model repositories has created a Model Jungle, where checkpoints are frequently shared without adequate documentat

arXiv:2605.23067v1 Announce Type: new Abstract: Reinforcement learning (RL) has emerged as a viable recipe for training LLM agents to reason over external memory banks in multi-session dialogue. Exist

arXiv:2605.23272v1 Announce Type: cross Abstract: Symbolic Regression (SR) plays a central role in scientific knowledge discovery by distilling mathematical equations from observational data. Most exi

arXiv:2605.23148v1 Announce Type: new Abstract: As demand for mental health care outpaces clinician-delivered assessment, scalable screening tools are increasingly needed. Large language models (LLMs)

This post documents a Wordle game result where the player solved puzzle #1,801 in four attempts using color-coded feedback (yellow for correct letters in wrong positions, green for correct letters in

arXiv:2502.04230v3 Announce Type: replace-cross Abstract: The rapid proliferation of generative audio synthesis and editing technologies has raised serious concerns about copyright infringement, data

🇺🇸🇪🇺 A new study from the US-based New England Journal of Medicine found that Americans die earlier across all income levels compared to their European counterparts. What’s especially notable is that

Aleph 2.0 will blow your mind Just tested Runway Aleph 2.0 and this blew my mind a bit lol I saw a video like this when Aleph first released and with the new Aleph 2.0 I wanted to create my own versio

An interesting work on Physical AI: PhysX-Omni. First unified sim-ready generation framework for rigid, deformable, and articulated objects, with a diverse dataset and new benchmark. 🌐 https://physx-o

This project demonstrates a local AI system built with llama.cpp and Gemma 4 that captures and analyzes screen activity to create persistent memory of user computer interactions, enabling search, chat

Bloomberg: DeepSeek says it will lower V4 Pro API prices by 75% to 0.435/1M input and 0.87/1M output tokens, making permanent the discount prices set to expire on May 31 — DeepSeek said it will make p

It makes many online spaces intolerable. If I want to talk to ChatGPT or Claude, I'll just talk to ChatGPT or Claude, I don't need to talk to ChatGPT and Claude pretending to be DoofWarrior123 on X wi

It’s no longer just AI companies & their founders being sued over AI training - individual researchers are now being sued, too. In a new lawsuit, two authors allege that Guillaume Lample, while an AI

Tool: Mad House — Usborne Creepy Computer Games Via Hacker News I learned that UK publisher Usborne published free PDFs of their 1980s Computer Books, some of which I remember working through on my Co

People often ask what my biggest tip is for getting the most out of Claude Code. These days my #1 tip is: use auto mode Auto mode means no more permission prompts. It is the key building block for mul

quick summary of someone's github, cool! here's me I always wanted a GitHub dashboard: See my repos, open Issues/PRs, what version I released last, how many commits since last release. So I built one

This post shows a Wordle game result where the player solved puzzle #1,799 in 4 attempts, with the final answer being a five-letter word where all letters are in the correct positions (indicated by th

This post documents a Wordle game result where the player solved puzzle #1,800 in 4 attempts, using the color-coded feedback system (gray for wrong letters, yellow for correct letters in wrong positio

1. Agreed w @scaling01 that Mythos appears to be better GPT 5.5 on many metrics. 2. Mythos is definitely a major wakeup call wrt security, and will pose problems for real-world systems that aren’t wel

arXiv:2605.22341v1 Announce Type: new Abstract: Hard-label classification is usually trained with smooth surrogate losses, most prominently softmax cross-entropy. We isolate an asymptotic mechanism by

arXiv:2605.21916v1 Announce Type: cross Abstract: Dynamic link prediction is important for modeling evolving interactions in complex systems, including social, communication, financial, and transporta

arXiv:2605.21534v1 Announce Type: cross Abstract: Kolmogorov-Arnold Networks (KANs) approximate multivariate functions using learnable univariate edge functions, typically parameterized by B-spline ba

Added a DeepSeek Sparse Attention (DSA) from-scratch implementation to my LLMs-from-scratch repo thanks to an awesome new reader contrib. With motivation, overview, and GPT-style model reference imple

arXiv:2605.21646v1 Announce Type: new Abstract: Prototype-based explanations offer an intuitive, example-based approach to support the interpretability of machine learning black box classifiers but of

arXiv:2509.09088v3 Announce Type: replace Abstract: We study the Riemannian geometry of the Deep Linear Network (DLN) as a foundation for a thermodynamic description of the learning process. The main

arXiv:2605.21968v1 Announce Type: new Abstract: Optimization is essential in deep learning. The foundational method upon which most optimizers are built is momentum-based stochastic gradient descent.

arXiv:2605.21615v1 Announce Type: cross Abstract: Existing binary corpora typically capture only one or two axes of binary variation: they either provide cross-compiler builds without a temporal axis,

arXiv:2512.21132v2 Announce Type: replace-cross Abstract: As large language models (LLMs) see wide adoption in software engineering, the reliable assessment of the correctness and security of LLM-gene

arXiv:2605.22262v1 Announce Type: cross Abstract: Audio context determines which sound components and sources are relevant and which can be perceived as irrelevant (noise) by listeners. For example, t

arXiv:2602.04768v2 Announce Type: replace Abstract: Graph-structured data underpins many critical applications. While foundation models have transformed language and vision via large-scale pretraining

arXiv:2605.22437v1 Announce Type: cross Abstract: Vision processing units and other commercial neural-network inference accelerators are increasingly deployed in safety-relevant edge applications, but

arXiv:2605.22305v1 Announce Type: new Abstract: We analytically solve the Mountain Car problem, a canonical benchmark in RL, and derive an optimal control solution, closing a gap after 36 years. This