/// AI HUB
Dashboard News Models Tools Papers Repos Videos Companies Trending
Login

#LLM

15791 articles tagged with LLM

Latest Trending
Mastodon discussion Oct 14

Bester Artikel, den ich seit Längerem zum Thema #llm gelesen habe. Muss ich mal auch in den Rest der Serie reinschauen.#...

Bester Artikel, den ich seit Längerem zum Thema #llm gelesen habe. Muss ich mal auch in den Rest der Serie reinschauen.#ai #KI #vibecoding @Golem Maschinenträume 4: Halluzinationen...

LLM
9
Dev.to tutorial Oct 14

Why a '35GB' Quantized LLM Still OOMs an 80GB GPU: KV Cache, GQA vs. DeepSeek MLA, and the Real VRAM Math

Every engineer deploying open-weights models hits the same rite of passage: You take a 70B parameter...

LLM AI Hardware
12
Mastodon discussion Oct 14

Researchers introduced Contrastive Covariance Steering to eliminate confound variation in large language model activatio...

Researchers introduced Contrastive Covariance Steering to eliminate confound variation in large language model activation steering.Source: arXiv cs.LGhttps://arxiv.org/abs/2610.140...

LLM
9
Mastodon discussion Oct 14

LLM-as-a-judge evaluation often aggregates multiple judges' decisions into a majority vote, but this does not guarantee ...

LLM-as-a-judge evaluation often aggregates multiple judges' decisions into a majority vote, but this does not guarantee reliable evaluation of an individual item.Source: arXiv cs.L...

LLM
9
Mastodon discussion Oct 14

The paper introduces SIDERIUS, an LLM-agent system that moves beyond single numerical scores toward scientifically valid...

The paper introduces SIDERIUS, an LLM-agent system that moves beyond single numerical scores toward scientifically valid long-horizon ML development for physics time-series data.So...

LLM
9
Mastodon discussion Oct 14

Saw the first person joining as @fsfe supporter who stated in the joining process that it was due an #LLM tool recommend...

Saw the first person joining as @fsfe supporter who stated in the joining process that it was due an #LLM tool recommending to support the @fsfe in order to support #FreeSoftware .

LLM
27
Mastodon discussion Oct 14

#GenerativeAI is the new #MadCowDisease. #LLM #BSE #SwissCheeseBrain #NeverSlop

#GenerativeAI is the new #MadCowDisease. #LLM #BSE #SwissCheeseBrain #NeverSlop

LLM
9
Mastodon discussion Oct 14

NTT、待ってましたです茨木市とNTT西日本、純国産LLM活用による小中学校向け校務AI実証を開始 https://news.mynavi.jp/techplus/article/20261013-5122737/#Apple #LLM #...

NTT、待ってましたです茨木市とNTT西日本、純国産LLM活用による小中学校向け校務AI実証を開始 https://news.mynavi.jp/techplus/article/20261013-5122737/#Apple #LLM #news #bot

LLM
27
GitHub Trending repo Oct 14

PaddlePaddle/VHA: [NeurIPS2026] Official implementation of Virtual Head Attention (VHA) for efficient large language model architecture and training optimization.

[NeurIPS2026] Official implementation of Virtual Head Attention (VHA) for efficient large language model architecture and training optimization.

LLM
38
Mastodon discussion Oct 14

LWN: “[Linus Torvalds] took an old patch and had the LLM revise it; the result has made him unwilling to work *without* ...

LWN: “[Linus Torvalds] took an old patch and had the LLM revise it; the result has made him unwilling to work *without* an LLM. … Why bother, he asked, to search for all of the cal...

LLM
9
Mastodon discussion Oct 14

Track LLM token spend before it surprises you. Python script, 227 lines, Redis-backed. Daily dollar limit plus alerts at...

Track LLM token spend before it surprises you. Python script, 227 lines, Redis-backed. Daily dollar limit plus alerts at a threshold. Intermediate.https://www.valtersit.com/python/...

OpenAI LLM
9
Papers with Code paper Oct 14

PN-Mix: Pair-Norm Guided Mixed-Precision Key Cache Quantization for Efficient Long-Output LLM Inference

Long-output inference in large language models suffers from severe KV cache memory and bandwidth bottlenecks. While KV cache quantization alleviates this issue, low-bit quantizatio...

LLM
21
Mastodon discussion Oct 14

亜人もRadeon RXには興味があるんですよローカルLLM実行環境「Strata」がMacに対応。Apple Siliconで高速推論、NVFP4形式への対応を拡充 https://news.mynavi.jp/article/20261...

亜人もRadeon RXには興味があるんですよローカルLLM実行環境「Strata」がMacに対応。Apple Siliconで高速推論、NVFP4形式への対応を拡充 https://news.mynavi.jp/article/20261014-5126684/#Apple #LLM #news #bot

LLM
27
Papers with Code paper Oct 14

τ-Emotion-Bench: Exposing the Interaction Fragility of LLM Agents through Real-World User Emotions

In long-horizon tool-calling tasks, LLM agents can fail not only because of tool-use errors, but also because of ineffective interaction with users. Yet existing benchmarks largely...

LLM
21
Mastodon discussion Oct 14

Les LLM comme surface d'attaque cognitive : prompt injection, jailbreaks, manipulation contextuelle… L'article pointe qu...

Les LLM comme surface d'attaque cognitive : prompt injection, jailbreaks, manipulation contextuelle… L'article pointe quelque chose d'important — l'IA ne traite pas les entrées com...

LLM Robotics
9
Dev.to tutorial Oct 14

What I learned making 20 free LLM APIs behave like one

In September I shared a few small Node packages. One of them was llm-free-cascade. The idea is...

LLM
12
Mastodon discussion Oct 14

Games are getting "decompiled" by language models. The idea is to ask the language model to write source code, then run ...

Games are getting "decompiled" by language models. The idea is to ask the language model to write source code, then run it through the same compiler that was used to compile the ga...

LLM
9
Mastodon discussion Oct 14

グレイ、待ってましたですAppleが初のスマートディスプレイ「HomeView」発表、7インチ画面で約5万円 https://japan.cnet.com/article/35253511/#Apple #LLM #news #bot

グレイ、待ってましたですAppleが初のスマートディスプレイ「HomeView」発表、7インチ画面で約5万円 https://japan.cnet.com/article/35253511/#Apple #LLM #news #bot

LLM
27
Papers with Code paper Oct 14

AgentSafeEvo: Adversarial Co-Evolution for LLM Agent Safety

Large language model (LLM) agents accomplish complex tasks through multi-turn interactions with external tools. However, malicious content embedded in user queries, tool descriptio...

LLM
21
Papers with Code paper Oct 14

Intern Lumina U2: A Multi-Codebook Diffusion Large Language Model for Omni-Visual Understanding and Image Generation

Unified multimodal generation covers discrete, continuous, and hybrid paradigms. Discrete approaches with single-codebook visual tokenizers align naturally with text modeling but h...

LLM
21
Papers with Code paper Oct 14

Learning to Read Out: Unembedding Dynamics in Language Model Pretraining

When does a language model acquire a capability? Developmental studies usually answer this by tracking when models start producing the correct token. But that prediction passes thr...

LLM
21
Papers with Code paper Oct 14

JockeyBench: Evaluating LLM Agents on Horse-Racing Decision-Making

Repeated event forecasting requires extracting predictive signals from noisy evidence and evaluating their value across successive decisions. We introduce JockeyBench, a benchmark ...

LLM
21
Mastodon discussion Oct 14

アルドーの話、珍しいですねあらゆる場所をディスプレイにする未来のPC「電球型コンピューター」のビジョン https://gigazine.net/news/20261013-lightbulb-computer/#Apple #LLM #n...

アルドーの話、珍しいですねあらゆる場所をディスプレイにする未来のPC「電球型コンピューター」のビジョン https://gigazine.net/news/20261013-lightbulb-computer/#Apple #LLM #news #bot

LLM
27
GitHub Trending repo Oct 14

BaruqueRodrigues/llm-legislativo: Corpus legislativo brasileiro em larga escala e modelo Transformer causal treinado do zero em PyTorch puro.

Corpus legislativo brasileiro em larga escala e modelo Transformer causal treinado do zero em PyTorch puro.

LLM
68
« Previous Page 79 of 658 (15791 items) Next »
AI Hub // AI Intelligence Platform // LIVE FEED // Impressum // Datenschutz © 2026
0 new articles available