Search: “papers”

Two weeks, one rule, and hundreds of entries from nearly 50 countries. Here's who took the four titles, and a look at everyone who made the final ten! Entries opened August 20 and closed September 1.

Automated lint: 12 errors, 53990 warnings, 3 info

Automated lint: 12 errors, 54839 warnings, 3 info

arXiv:2609.13073v1 Announce Type: cross Abstract: Recent breakthroughs in LLM-based systems and their abilities in problem solving and coding have allowed progress in the AI for Science paradigm, pote

Automated lint: 14 errors, 54840 warnings, 3 info

Automated lint: 17 errors, 59669 warnings, 3 info

Code review has to change for coding agents. Why? For me, it’s about scaling coding reviews while ensuring quality. If you give a coding agent one task, it can return several pull requests across diff

Automated lint: 19 errors, 64915 warnings, 3 info

Automated lint: 12 errors, 53990 warnings, 3 info

I like this framing a lot: agent improvement is harness improvement, not model improvement The interesting interventions are often at the tool boundary: - what context you pass - when tools are provid

Automated lint: 12 errors, 54839 warnings, 3 info

On building an agent harness from scratch. Got so many questions about where to get started. My short guide (feed it to your agent): If you really want to learn harnesses well, it's worth building one

Automated lint: 14 errors, 54840 warnings, 3 info

Automated lint: 17 errors, 59669 warnings, 3 info

Automated lint: 19 errors, 64915 warnings, 3 info

You ship an agent. It mostly works. Then the feedback loop becomes a support ticket: a user got the wrong answer, a tool call looped four times, a refund went out that shouldn’t have. Standard observa

arXiv:2609.18120v1 Announce Type: cross Abstract: AI-driven penetration testing has been demonstrated with premium frontier models such as GPT-4, but the per-engagement token cost makes continuous, au

What if you don’t need a new model to get Jev-style decisions? I built hearim(헤아림. hea-a-rim. not Here, I am.. lol), an open-source gateway that turns ordinary local or hosted LLMs into a Jev-compatib

Good day data nerds! I am trying to get more into running models, learning about agentic workflows, and creating my own tools. But as you do (right?) I had to fine tune my current setup. With the way

arXiv:2608.00008v2 Announce Type: replace Abstract: The local deployment of large language models (LLMs) is gaining traction due to privacy concerns and the desire for on-premise inference. However, t

Meet Bev. She is a decision model (the Jev / Nimble kind: you give her a situation and a question, she gives a probability for each answer), fine-tuned on Qwen3.5-9B to pick the worst answer on purpos

Next YC Paper Club: Inference Inference is no longer just: y = model.forward(x) It has now become as complex and important as training. The difference between naive inference and well tuned could be 1

In my attempt to combat powerty; as electricity cost a ton these days and it is hot as hell, I consolidated 2 machines into one, so my 2 crappy machines now are one, and that means a bit less power an

I've made a few posts recently, just talking about the hardware I've got and the model I use. Pair of P100s, Unsloth Qwen3.6 35b A3B UD Q4 K XL. There's been a ton of talk of model and hardware specif

Social and low-evidence quarantine moved to raw as rejected. 168 high-specificity articles remain in inbox; four sources were filed.

Automated lint: 14 errors, 54840 warnings, 3 info

arXiv:2609.27037v1 Announce Type: new Abstract: Wake word detection is a critical component of virtual assistants, serving as the gateway to seamless user interactions. This paper introduces a novel w

Automated lint: 17 errors, 59669 warnings, 3 info

The browser has changed significantly. Rather than just a window to the web, it serves as an AI workspace and central operating environment for the modern enterprise. With knowledge workers spending o

Last week we launched DigitalOcean Managed Agents in public preview: a managed runtime, governed access to more than 16,000 tools, serverless inference, and persistent memory and storage, all on one c

Automated lint: 19 errors, 64915 warnings, 3 info

arXiv:2610.04784v1 Announce Type: cross Abstract: Traffic classification (TC) is crucial to secure Internet of Things (IoT) networks, whose edge nodes often operate under privacy, bandwidth, and energ

The largest agentic LLM Inference dataset has arrived! 206B tokens · 12,002 sessions · 1,186,582 LLM requests · 1,213,347 tool calls The traces include tool names, arguments, durations, and more. Expl

Lunara introduces a novel Diffusion Mixture Transformer architecture with fewer than 10B active parameters for modeling artistic intelligence in image generation. Its CAT training algorithm iterativel

TRL v1.15 is out, and it’s an absolute banger of a release for memory-efficient post-training. The main change: SFT, DPO, KTO, GRPO, RLOO and Distillation now use a fused LM head by default. Instead o

Figure 1b from our paper Disclosure: I'm one of the authors (Microsoft). The paper, code, dataset are public and ThinkingBox is on Hugging Face OpenEnv as well. Raw evaluation trajectories are not rel

Conditional memory architectures such as DeepSeek Engram use input n-grams to look up learned embeddings, expanding the capacity of large language models (LLMs) with limited additional computation. Be

Nvidia Corp. is in early talks to acquire open-weight model developer Reflection AI Inc. or invest more in the startup, according to the Financial Times. People familiar with the matter told the paper

LTX-2.5 makes a video with one mixed soundtrack. Our LoRA also outputs one track per captioned sound, in the same run. Prompt 'a jeep, its engine growling' and 'a taxi, its horn honking' and you get t

🧬 🤗 A new atlas of microproteins in the human brain is now @huggingface! It brings together more than 1,000 microproteins, including one that’s reduced in Alzheimer’s and appears to play a role in how