MLINFO COLLECTION
LoRA、RLHF、SFT、軽量ファインチューニングなど、LLMを用途に合わせる技術を扱います。
Extending Vision-Language-Action models (VLAs) to humanoid robots requires coordinated whole-body control and diverse demonstrations that are costly to collect in real-world scenarios. Although…
HoloBoxing presents a simple recipe for learning humanoid boxing by building on a pretrained whole-body controller. The recipe separates reusable motor skills from task decisions: a compact planner…
Many language-model pipelines end in a closed-set decision, such as selecting a tool. Prompting a large language model for it is slow and order-sensitive.
Frontier black-box Large Language Model (LLM) agents are proficient at long-horizon reasoning and precise action generation. However, when it comes to a specific agentic task, they have no…
Computer-use agents are limited by the interfaces humans give them. An agent may type a spreadsheet cell by cell when a single line of code would do, or print all two thousand lines of a file through…
Agents need reliable ways to validate their outputs, both when completing tasks and when filtering synthetic training data. We study verifier generation: from the instruction and environment…
Harness development plays a crucial role in building capable AI agents. Recent approaches improve harnesses through recursive self-improvement (RSI), but their performance gains often come with…
この論文では、現在のVision-Language-Benchmark（VLB）を超える、MLLMがアクティブな観察を実演できるようにするためのバenchmark、ActiveVisionを提案する。このActiveVisionは、人間の視覚が閉じたループであるという事実に基づいて、観察対象物の予測を実行するために、視覚と言語を相互に関連させ、対象物にアクセスする。
AIを使ったwebスクレイピングツールです。
学習中のアイデアや知識を整理するための日記。
AIパワードシステムやデータパイプラインの監視と評価を行うための、オープンソースのMLとLLMの観測性フレームワーク。
Even a carefully proofread paper can leave small gaps in its proofs or its stated assumptions. We introduce PaperFormalizer, a Lean-based agentic pipeline that helps authors find and close such gaps…
Lyapunov functions and barrier certificates give state-space guarantees of stability and safety, but synthesizing and verifying them---especially for nonlinear, high-dimensional systems---remains an…
Fine-grained multimodal intelligence requires models to both understand a designated region and localize it from language. Existing methods learn these directions with separate objectives and…
People adapt how they talk to the person in front of them. However, chat models tend to respond in Standard English regardless of the dialect used by the user.
In this paper, we systematically investigate the mechanisms, scaling behavior, and generalization of physical Recursive self-improvement. We introduce PhysRSI-eval to quantify physical RSI through a…
Streaming video world models generate the future chunk by chunk, conditioned on their own past and a stream of actions. Trained on short clips, they drift once a rollout exceeds the training horizon,…
LLM routing dynamically selects and coordinates heterogeneous language models across diverse tasks. However, existing approaches are largely built around a predefined execution paradigm, such as…
Can large language model (LLM) agents deliver expert-level operations research (OR) solutions directly from original client materials, without prior expert reformulation? Existing OR benchmarks…
Large language model (LLM) agents have shown promising potential in coding tasks, and their performance is jointly determined by the policy model and the harness that mediates their interaction with…
大規模言語モデルのテスト時間調整に関する調査のリポジトリ。
Deep research systems iteratively plan, gather evidence, synthesize, and revise, making end-to-end latency a key bottleneck for interactive use. Almost all production systems are built on…
LLM agents are commonly trained with RLVR, but the sparse nature of typical RLVR rewards makes credit assignment challenging, especially for long-horizon tasks. We propose Self-Credit, an end-to-end…
Language models can make personalized recommendations from rich item content, user history, and feedback. However, evaluating many candidates with full-text inputs incurs substantial online…