Search: “agents”

arXiv:2604.22230v1 Announce Type: cross Abstract: Benchmark hacking refers to tuning a machine learning model to score highly on certain evaluation criteria without improving true generalization or fa

People keep blaming the users for the growing number of vibe-coded reasoners. Doing so is *half* right. Users *are*screwing up - by letting vibe coded stuff access their files, without proper backups,

arXiv:2511.14427v3 Announce Type: replace-cross Abstract: Effective contact-rich manipulation requires robots to synergistically leverage vision, force, and proprioception. However, Reinforcement Lear

.@swyx on whether AI infrastructure has finally stabilized: Media Always enjoy getting to chat with @swyx on our annual cross-episode with @latentspacepod on the state of AI. We hit on what’s shifted,

arXiv:2510.07632v2 Announce Type: replace Abstract: Frontier AI models have achieved remarkable progress, yet recent studies suggest they struggle with compositional reasoning, often performing at or

The artificial intelligence arms race has spent the last two years obsessed with a duopoly of constraints: the desperate hunt for Nvidia Corp. silicon and the grueling wait for grid-scale megawatts. I

arXiv:2604.22260v1 Announce Type: cross Abstract: Urban transportation systems face growing safety challenges that require scalable intelligence for emerging smart mobility infrastructures. While rece

Continued weak spots of AI, from the point of view of a business professional and not a PhD biochemist: 1) SVGs. The ability to 'illustrate' and have that thing be infinitely scalable. See below image

I am increasingly bullish on open source harnesses (like OpenCode) not because they will be better than SOTA closed harnesses, but because they will never pull shady stuff like what Claude Code and ot

Opened a llama.cpp discussion about whether custom GBNF grammars can compose with tool calls in llama-server. Right now tools work alone, grammar works alone, but tools+grammar doesn't. If you use lla

The community can now download pre-quantized weights from MLX community repo on HF thanks to @LambdaAPI Model collection: https://huggingface.co/collections/mlx-community/deepseek-v4 DeepSeek-V4-Flash

GPT-5.5 prompting guide Now that GPT-5.5 is available in the API, OpenAI have released a wealth of useful tips on how best to prompt the new model. Here's a neat trick they recommend for applications

Launching pyptx — a Python DSL for writing NVIDIA PTX kernels. One PTX instruction = one Python call. Write pure PTX in Python. Direct Hopper + Blackwell support: wgmma, TMA, tcgen05, mbarriers. JAX +

Local models do seem likely to create an explosion of new use cases. Local compute >> cloud compute. This is where we are right now. And i’m not gonna lie it feels pretty magical 🧚‍♀️ Qwen3.6 27B runn

Fireworks AI posted a question to their audience asking what features or capabilities they would like to see developed next, with a specific mention of full parameter tuning as a potential option. Thi

4⃣4⃣4⃣4⃣ Introducing DeepSeek V4 Pro, a long-context model with hybrid attention, three reasoning modes, and SOTA coding performance. AI natives can now use DeepSeek V4 Pro on Together AI and benefit

arXiv:2604.21688v1 Announce Type: cross Abstract: The IC3 algorithm represents the state-of-the-art (SOTA) hardware model checking technique, owing to its robust performance and scalability. A signifi

This article describes a technique for accelerating reinforcement learning (RL) rollouts using distribution-aware speculative decoding, which can achieve up to 50% speedup improvements. The method lik

arXiv:2604.20932v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) systems are increasingly deployed in sensitive domains such as healthcare and law, where they rely on private, do

arXiv:2504.03476v2 Announce Type: replace Abstract: Accurate lumbar spine segmentation is crucial for diagnosing spinal disorders. Existing methods typically use coarse-grained segmentation strategies

Developers can build with DeepSeek V4 through NVIDIA GPU-accelerated endpoints on build.nvidia.com, with hosted endpoints providing a fast way to prototype before moving to self-hosted deployment. Dee

arXiv:2604.21352v1 Announce Type: new Abstract: Mental health challenges are increasing worldwide, straining emotional support services and leading to counselor overload. This can result in delayed re

Cloud-hosted models will become more niche/seldom-used as much cheaper local models fulfill that which 90% of consumers need from AI. Lots of models to buy/use, but very few hardware options upon whic

Marina Temkin / TechCrunch: ComfyUI, which gives creators granular control over image, video, and audio outputs from diffusion models, raised 30M at a 500M valuation — ComfyUI, a startup that helps cr

Congrats to @deepseek_ai team! Doing the numbers I would estimate: Pro < 14m for the final training run Flash < 4m Ratio of active params x total training tokens vs v3 Total compute costs (data prep,

Raphael Satter / Reuters: Diplomatic cable: US State Department has ordered a global push to bring attention to what it says are efforts by Chinese companies to steal IP from US AI labs — The U.S. Sta

arXiv:2411.00171v2 Announce Type: replace Abstract: To avoid myopic behavior, multi-step lookahead Bayesian optimization (BO) algorithms consider the sequential nature of BO and have demonstrated prom

arXiv:2506.19579v3 Announce Type: replace-cross Abstract: Robotic scene understanding increasingly relies on Vision-Language Models (VLMs) to generate natural language descriptions of the environment.

arXiv:2506.09998v2 Announce Type: replace-cross Abstract: Large language models (LLMs) can often accurately describe probability distributions using natural language, yet they still struggle to genera

For the last 72 hours since ml-intern launched we have had over 500+ autonomous AI research projects running on the Space at all times. Some insane ones I saw: 1. A new AI paradigm from scratch — tryi

arXiv:2604.21391v1 Announce Type: cross Abstract: Bridging high-level semantic understanding with low-level physical control remains a persistent challenge in embodied intelligence, stemming from the

arXiv:2604.21192v1 Announce Type: cross Abstract: Vision-language-action models (VLAs) have been extensively used in robotics applications, achieving great success in various manipulation problems. Mo

Introducing DeepSeek V4 Pro, a long-context model with hybrid attention, three reasoning modes, and SOTA coding performance. AI natives can now use DeepSeek V4 Pro on Together AI and benefit from reli

Just merged a built-in skill for Google's DESIGN.md A skill that lets Hermes author, lint, diff, and export DESIGN.md files, giving it fluency in Google's new open-source visual-identity format the mo

arXiv:2604.20859v1 Announce Type: cross Abstract: Recent literature highlights the potential of graph-based approaches within large language model (LLM) retrieval-augmented generation (RAG) pipelines

arXiv:2603.06545v2 Announce Type: replace-cross Abstract: We present LiveSense - a cross-platform that transforms a commercial off-the-shelf (COTS) Wi-Fi Network Interface Card (NIC) on a laptop into

arXiv:2604.20871v1 Announce Type: cross Abstract: We introduce M-CARE (Model Clinical Assessment and Reporting for Evaluation), a clinical case report framework for AI model behavioral disorders adapt

arXiv:2604.21871v1 Announce Type: new Abstract: Human moral judgment is context-dependent and modulated by interpersonal relationships. As large language models (LLMs) increasingly function as decisio

arXiv:2604.21564v1 Announce Type: new Abstract: Large language models increasingly shape the information people consume: they are embedded in search, consulted for professional advice, deployed as age

arXiv:2604.21092v1 Announce Type: new Abstract: Integrating Large Language Models (LLMs) into complex software systems enables the generation of human-understandable explanations of opaque AI processe

Models are changing really fast, often in ways that will break your product and technical assumptions. There's no way around this – the only way forward is to relentlessly iterate to make sure you're

CursorBench is a benchmarking tool or evaluation framework developed by Cursor, likely designed to measure and compare the performance of AI code completion or development features. The post provides

New episode of The Information Bottleneck is out, this time with @liuzhuang1234 (Princeton). We talked about ConvNeXt and whether architecture still matters; dataset bias and what 'good data' actually

arXiv:2604.21510v1 Announce Type: new Abstract: While Large Language Models (LLMs) demonstrate remarkable reasoning, complex optimization tasks remain challenging, requiring domain knowledge and robus

arXiv:2604.21481v1 Announce Type: new Abstract: Crowdsourced pairwise evaluation has emerged as a scalable approach for assessing foundation models. However, applying it to Text to Speech(TTS) introdu

arXiv:2604.21232v1 Announce Type: new Abstract: Vision-Language-Action systems follow instructions to execute multi-step tasks in multimodal environments. Recent VLA approaches typically rely on post-