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。
マルチモーダル理解技術のための新しいアプローチであるMIRRORを提案しました。MIRRORは、テキスト、図、テキストと図の組み合わせから等価な視点を提供することで、視覚的な推論や複雑な推論力を向上し、さまざまなモデルのバリエーションを取り入れることを可能にします。
Critic-free methods are widely used in reinforcement learning with verifiable rewards (RLVR) for long chain-of-thought (CoT) reasoning, avoiding difficult and costly critic training. Common…
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…
Localized AI manipulations in long-form videos often affect brief events within otherwise authentic content, making video-level classification insufficient for forensic analysis. Existing…
Large Language Model (LLM) agents can handle increasingly complex tasks, navigating long trajectories of observations and actions. As these trajectories grow, key-value (KV) cache I/O and storage…
Brain encoding models aim to predict neural responses to stimuli. The most widely used approach fits readouts from frozen pretrained backbones.
Open-source code for training and scaling up energy-based foundation models.
Mixture-of-Experts (MoE) models are bottlenecked by loading routed-expert weights from memory during interactive decoding at small batch sizes. Because most intermediate channels in a routed expert…
Generative models increasingly expose a reasoning effort setting that lets users scale inference-time compute, trading higher cost for potentially improved performance. Users must choose an effort…
Reinforcement learning (RL) has emerged as the primary paradigm for optimizing Large Language Model (LLM) agents, yet efficient critic-free algorithms (e.g., GRPO) suffer from a fundamental uniform…
Can AI agents autonomously train useful language models and improve them using feedback from users? We introduce RSI Arena, a two-stage study of autonomous post-training as a step toward recursive…
Learning visual design is essential for prompt enhancement (PE) to turn underspecified user requests into coherent visual specifications for text-to-image (T2I) generation. Existing methods preserve…
LLMのマージに関してのマニュアルです。理論、方法、応用などについての概要が記載されています。
エージェントRRLに関連するアワーショットリスト。
Spatial intelligence requires agents to actively acquire visual evidence and integrate observations into a coherent representation of the three-dimensional world. Yet spatial question answering…
Financial agents must form forecasts and investment judgments from decision-time evidence, with predictions evaluated against subsequent outcomes. Existing benchmarks assess financial knowledge,…
Multi-Token Prediction (MTP) is now a common ingredient in language-model pre-training, as it improves downstream performance and enables faster inference through speculative decoding. We identify a…
Web agents require diverse, executable, and resettable website environments for reproducible training and evaluation. Human-assisted mirrors demand per-site engineering, while generative construction…
Omnimodal large language models (Omni-LLMs) are increasingly expected to assist users while observing continuous audiovisual streams. However, existing evaluations provide limited insight into how…
Evaluating human-AI co-design requires testing whether coding agents can translate real users' multimodal requests into working application revisions. We introduce Co-Design Bench, a reference-free…
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…
デバイス上のLLM推論をXビット量化を使用したもの。
Scientific discovery requires identifying the scientific principles underlying observed phenomena to guide further investigation. As these empirical principles are often unknown in complex discovery…
Spatial reasoning asks a model to work out where objects are in 3D space, how they relate to one another, and how they move. Agentic VLMs have recently brought large improvements on such tasks by…