MLINFO COLLECTION
日次更新の新着・公開記事を新しい順に掲載しています。
Long-horizon LLM agents interact with their environments through complete assistant turns while generating each action token by token. We observe that critic values vary primarily across turns,…
Long-video generators increasingly retrieve past visual observations to prevent identity drift. The intuition is compelling: more access to history should make future video more consistent.
Physical reasoning underpins how embodied systems understand and act in the physical world, yet vision-language models (VLMs) remain unreliable on questions about dynamics and physical causality.…
Outcome RL raises pass@1 but not pass@k at large k (Yue et al., 2025). But every pass@1 is scored under a token budget.
An agent that truly knows and acts on behalf of its user has been a long-standing promise of AI assistants. Computer-use agents bring this promise within reach by capably executing fully specified…
Long-horizon agents continuously encounter reusable procedural knowledge, yet existing systems typically rely either on model adaptation or external memory, trading persistent learning for rapid…
AI agents must decide when another search is worth its cost. Answer-success probabilities capture question difficulty, while this decision requires estimating the additional benefit of search.
Safe household navigation requires robots to regulate clearance and speed according to what an obstacle is and how close it is, without unnecessary conservatism. Yet existing evaluations do not test…
Vision-language models are shifting from offline passive understanding toward online proactive interaction. However, prevailing methods largely rely on explicit requests while miss the implicit user…
Language model agents often abandon correct work when a user challenges it, yet simply telling them to stand firm makes them ignore real mistakes. Once an agent reads a complaint, it tends to…
Despite rapid advances in large language models (LLMs), their deployment in the sports and health domain remains high-risk due to the absence of domain-specific evaluation benchmarks. Existing…
Diffusion language models (DLMs) promise parallel text generation, but in practice face an unresolved speed-quality trade-off. Exact decoding fills in only one masked position per model pass, while…
How much of zero-shot benchmark accuracy is captured by word-level alignment between a pre-training corpus and the benchmark target? We study this question through word-level unigram cross-entropy…
ARTは、多段強化学習トレーナーです。このトレーナーは、GRPOを使用して、現実世界のタスクに対して、多段強化学習を行うことができます。
AIドライブのマルチエージェント研究アシスタント。仮説の生成、データ分析、およびレポートの生成を自動化する。
ゼネレーティブAIに関連するリソースの一覧。
kserveは、分散型生成的および予測性AI推論プラットフォームであり、可 scale, multi-framework デプロイをサポートして Kubernetes 上に展開されることができます。
This repository collects an extensive list of awesome papers about Story Generation / Storytelling, exclusively focusing on the era of Large Language Models (LLMs).
OpenAIに互換性があり、Cloud APIとして利用できるLLM。
最新のマシンラーニング研究論文を紹介している。
このリポジトリでは、LLMベースのエージェントアプリケーションのための強化学習の橋渡しを提供しています。
A curated collection of papers, benchmarks, surveys, and tools for model quantization, covering low-bit networks, LLMs, multimodal and generative models, vector and lattice quantization, and efficient
Fault-tolerant, highly scalable GPU orchestration, and a machine learning framework designed for training models with billions to trillions of parameters
Replicator dynamics, the central model of evolutionary game theory, describe populations evolving under selection and agents learning by trial and error. They also admit a third use: continuous-time…