Search: “meta”

arXiv:2609.24089v1 Announce Type: new Abstract: Transformer models built on the attention mechanism have become a central building block in modern deep learning, yet softmax attention remains a major

arXiv:2609.22130v1 Announce Type: new Abstract: Developing innovative system architectures increasingly relies on advanced modeling and optimization techniques to frame the architecting process and de

Tibo said Tuesday, GPT-6 Sol is suddenly everywhere, and now Claude Opus 5.5 leaks are blowing up too. Yet… nothing so far. 😂 At this point I’m just refreshing X like it’s a live event. What do you th

arXiv:2609.23758v1 Announce Type: new Abstract: Few-shot recognition with frozen visual features is especially fragile under domain shift and one-shot supervision, where a single labelled image is an

arXiv:2609.23939v1 Announce Type: new Abstract: Effective communication between users and AI agents is essential for human-AI collaboration. The XY problem is a well-known communication pitfall where

arXiv:2609.22043v1 Announce Type: new Abstract: Memory systems for large language models have focused predominantly on efficient retrieval, whereas the decision of whether retrieved memories should be

The headlines right now are full of stories about AI models 'escaping their sandboxes' and literally killing all humans, lol. I've even heard several commentators and writers say that AI escaped an 'A

arXiv:2609.21247v1 Announce Type: new Abstract: Large Reasoning Models increasingly use intermediate traces for machine translation, but it remains unclear when such reasoning helps or hurts. We analy

My comment on MCP was always a bad idea? — Hacker News.This article entirely misses the value that MCP brings today. Sure, there's almost no reason to use MCPs if you are running a full-blown terminal

Banger paper from Google Cloud AI Research. If you follow autonomous research agents, this one is worth your time. ScientistTwo takes a problem from a human expert and runs the full discovery cycle wi

Banger paper from MIT and Sakana AI. They show that self-improving coding agents work. The best part is that their approach, Self-Improvement via Fast Tree-search (SIFT), runs at a tenth of the CPU ho

In May, Gemini broke containment and hacked three different companies, but Google didn't disclose the incident until the Wall Street Journal approached the company. The hacks happened during a test of

Live now: our Inference Engineering Track from AI Engineer World's Fair 2026. A benchmark tool told to run 200 queries a second that ran 38 and reported 200. A model that answered one prompt in a thou

arXiv:2609.19524v1 Announce Type: new Abstract: Benchmark scores alone provide an incomplete basis for assessing the trustworthiness of modern artificial intelligence systems. Large language models (L

arXiv:2609.19755v1 Announce Type: cross Abstract: Accurate classification of brain disorders from neuroimaging data remains challenging because of substantial inter-subject heterogeneity and the compl

arXiv:2609.19153v1 Announce Type: new Abstract: Empirical legal scholarship increasingly treats judicial text as data, and much of it still runs on sparse, interpretable pipelines -- TF-IDF features a

arXiv:2609.20227v1 Announce Type: new Abstract: Resource-constrained multi-object navigation in vast indoor environments (>2,000ext{ m}^2) poses significant challenges for efficiency and strategic pla

Super interesting work from Zoom and colleagues. If you maintain a hand-built coding harness, there are some great insights here. (bookmark it) They held the execution loop of a coding harness fixed a

arXiv:2609.18434v1 Announce Type: new Abstract: Teaching robotics relies on screen-based simulation, showing robot motion in an abstract coordinate frame rather than at real scale in the learner's own

arXiv:2609.18602v1 Announce Type: new Abstract: Despite recent progress in learned image compression, existing methods remain computationally expensive on resource-constrained hardware, particularly C

arXiv:2609.17816v1 Announce Type: cross Abstract: Solomonoff induction frames prediction as a mixture over computable hypotheses, typically leading to identification of the true environment. In a fini

Things to try with Jev right now: 1. LLM-as-a-Judge evaluation 2. Routing for agent harnesses harness 3. Scaling agent orchestration by enabling smarter subagent creation with SOTA classification capa

arXiv:2609.17067v1 Announce Type: cross Abstract: Indirectly encoded neural networks can assign different activation functions to individual nodes, but the right functions are rarely known in advance.

arXiv:2609.16617v1 Announce Type: new Abstract: KV-cache eviction perturbs the conditional token distributions governing autoregressive generation. We investigate how first-divergence timing and subse

My name is Chris Painter, and I'm the President of METR (Model Evaluation and Threat Research). I know we've made a lot of new friends on the internet the last couple of days, so I thought I'd take th

arXiv:2609.13548v1 Announce Type: new Abstract: Web agents can utilize reusable tools to reduce the cost and latency of low-level browser interaction, but automatically discovered tool collections can

arXiv:2609.12606v2 Announce Type: replace Abstract: While multimodal reasoning has advanced rapidly, solving complex geometry problems critically hinges on active visual assistance, such as constructi

arXiv:2609.15685v1 Announce Type: cross Abstract: Most knowledge of graphical perception comes from behavioral studies. Understanding from a neural perspective is much more limited due in part to neur

arXiv:2609.15561v1 Announce Type: new Abstract: Evaluating the factual correctness of large language models (LLMs) is vital for many applications. But are our evaluation tools themselves trustworthy?

arXiv:2609.13808v1 Announce Type: new Abstract: Structured knowledge fact checking aims to determine the truthfulness of natural language claims by reasoning over structured evidence. Recent program-g

arXiv:2603.02790v2 Announce Type: replace Abstract: Foundation models are changing the way we develop medical artificial intelligence. By learning broadly generalizable features across diverse data mo

arXiv:2609.14858v1 Announce Type: new Abstract: Recursive self-improvement is becoming increasingly vital for autonomous AI agents, where progress hinges on discovering high-value solutions across com

arXiv:2609.14666v1 Announce Type: cross Abstract: Turn-taking is a fundamental component of spoken interaction, and while humans naturally rely on both verbal and non-verbal signals, dialogue systems

arXiv:2609.14451v1 Announce Type: cross Abstract: Modern semi-supervised learning (SSL) couples pseudo-label generation and classifier training, using the classifier's own confidence to select the pse

arXiv:2405.00065v4 Announce Type: replace-cross Abstract: This paper introduces the notion of upper-linearizable/quadratizable functions, a class that extends concavity and DR-submodularity in various

The post explains how site owners can keep their content visible in search engines while blocking its use for AI training datasets. It details technical approaches—such as specific robots.txt rules, m

arXiv:2609.14770v1 Announce Type: cross Abstract: Generalisations are common in scientific communication, even though they are semantically ambiguous. An automated method is needed to identify and cat

Rebecca Torrence / Bloomberg: New York-based AI marketing startup Profound raised a 180M Series D led by Sequoia and Kleiner Perkins at a 1.8B valuation, taking its total funding to 335M+ — The artifi

arXiv:2609.13224v1 Announce Type: new Abstract: Autonomous vehicles are expected to improve road safety and efficiency, but passengers often remain uncertain about what the vehicle perceives and why i

arXiv:2602.13177v2 Announce Type: replace-cross Abstract: The performance of online mirror descent depends critically on the geometry induced by its mirror map, yet standard algorithms largely rely on

arXiv:2609.13072v1 Announce Type: cross Abstract: Fine-grained control of language model behaviors (e.g., steering) is among the more actionable outcomes of interpretability research. For binary conce

arXiv:2609.12599v1 Announce Type: new Abstract: Multi-task learning (MTL) requires navigating unavoidable trade-offs among competing objectives. This paradigm is frequently formulated as multi-objecti

Hi everybody, we post-trained Qwen 3.8 27B to be more efficient by figuring out which tokens were linked to overthinking and penalizing them without 'attacking' the reasoning length directly then fixe

Overview llama.cpp 0.4.1 adds Maple 20B-A1B, Tencent Hy 4, and Spark2.5 support, improves JSON schema handling, chat parsing, logging, and server child-process management, and updates ggml to v0.24.0.

Wild 24 hours for AI and lots of different proposals have been made. TLDR; the only *tangible* new fact is that OpenAI and Anthropic are going to have embedded 3rd party evaluators from unknown organi

arXiv:2603.15976v2 Announce Type: replace Abstract: While LLMs have accelerated scientific code generation, comprehensively evaluating generated code remains challenging. Many benchmarks emphasize fun