Speculative Diffusion is a Tale of Two Tradeoffs
Speculative decoding is a technique that accelerates the inference speed of autoregressive large language models (LLMs) by sampling from a faster, lower quality draft model. Traditionally, a…
nlp
MLINFO COLLECTION
LLM Fine-tuning
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。
記事一覧
6 / 36DirCast: Live Esports Directing and Commentary with a Single Streaming Video-Language Model
A live esports broadcast needs a director who chooses which camera goes on air and a caster who talks over that choice, every second and without knowing what comes next. Streaming video language…
nlp
LaLa-World: Scaling Latent World Models with Natural Language Actions
This paper shows that JEPA-style latent world models (LWMs) can learn across diverse domains and data sources by adopting the language-conditioned interface of video generation models. We establish…
deep-learning
SolarRenderer: Few-Step Generative Reference Rendering
Game engines and coding agents can specify the layout, motion, and camera of a scene, yet turning such coarse structure into realistic video requires a renderer that follows the structure and…
deep-learning
SO-101 Bench: Accessible Spatial Manipulation
Low-cost arms such as the SO-101 have become the most common entry point to robot learning, yet no released policy performs spatially constrained, language-conditioned tasks on them out of the box,…
nlp
Rethinking Verification in Agent Harnesses
Agent harnesses enable large language models to act through tools, observe the results, and iteratively work toward a task goal. Verification checks and revises agents' work to improve output quality.
nlp
RoboJev: An Open Vision-Language Judge for Robot Success Detection
Many robot manipulation videos do not indicate whether the task was successfully completed. RoboJev-27B is an open-weight vision-language model that takes a task instruction, 10 frames of a…
nlp
Novel or Not? PatEx-Gym: Agentic Prior-Art Search for Novelty Assessment in Patent Examination
Patent examination is a challenging real-world task that requires agents to discover sparse prior art, iteratively refine queries, inspect technical evidence, and produce novelty assessments…
deep-learning
AdaPRA: Process Reward Agents with Adaptive Rubrics for Data Science
Data science agents can automate end-to-end machine learning workflows, yet they remain far from competitive on human leaderboards. Agents make process errors such as insufficient exploration,…
nlp
DraMaze: A Multi-Agent Pipeline with Future-Aware Memory for Diverse Microdrama Script Generation
The rapid growth of microdramas has increased demand for high-quality script production. Long-form microdrama script generation with LLMs requires both diverse plot progression and long-range…
nlp
Every Weight Is a Path of Shared Discrete Decisions
We introduce TWIG (Tree-structured Weights with Inherited Gates), a representation in which every weight of a neural network is the end of a path of small discrete decisions: a sign, a shift by a…
deep-learning
Evaluating DeepSeek V4.1 Flash-1017 for loss of control and harmful manipulation risks
As frontier language models grow increasingly capable and autonomous, independent third-party evaluations are critical for characterizing their systemic safety risks. While closed-source releases are…
nlp
dafeiyu-cleaner — DeepSeek 蓝色大肥鱼消除计划：识别并清理 B 站（Bilibili）评论区中由 DeepSeek 大模型、AI Agent 驱动的机器人账号（大肥鱼）的 Chrome / Edge / Firefox 浏览器插件。离线规则 + DeepSeek API 精判，AI 评论检测、空间主页鉴定、鲸鱼娘一键清场。DeepSeek AI bot detector for Bilibili comments.
DeepSeek 蓝色大肥鱼消除计划：识别并清理 B 站（Bilibili）评论区中由 DeepSeek 大模型、AI Agent 驱动的机器人账号（大肥鱼）的 Chrome / Edge / Firefox 浏览器插件。离线规则 + DeepSeek API 精判，AI 评论检测、空间主页鉴定、鲸鱼娘一键清场。DeepSeek AI bot detector for Bilibili comme
nlp
VibeGame: Prompt-to-Game Development with AI-Native Engine and Self-Evolving Adversarial Agent Team
Large language model agents have enabled software development through natural-language interaction, but extending this paradigm to end-to-end game development remains challenging. Building a playable…
nlp
MMVistaReason: Toward Open-Data and Post-Training Recipes for Multimodal Reasoning
Open multimodal reasoning models have benefited from large-scale reasoning supervision, yet reliable post-training remains challenging due to uneven data quality, inefficient supervision…
deep-learning
CausalAlign: Causal Alignment of Video Generation Models for Consistent Ego-Motion
Diffusion-based video generation models (VGMs) can produce visually plausible videos, yet their camera ego-motion often drifts over long horizons. Camera ego-motion determines how the viewpoint…
nlp
TenetBench: A Clause-Anchored Russian Corpus for Evaluating Language Models against Professional Codes of Ethics
Codes of professional ethics guide and restrict specialists, who increasingly work with assistants built on large language models. Such an assistant can breach the user's code, or help the user…
nlp
EvaOmni: An Evidence-Grounded Benchmark for Audio-Visual Reasoning
Omni LLMs can naturally locate key audio and visual evidence and integrate information across modalities for audiovisual reasoning. Existing audio-visual reasoning benchmarks that mainly rely on…
nlp
Code2Video-Compass: A Comprehensive Benchmark for General-Purpose Code-Based Video Generation across T2V, I2V, and V2V
Code-based video generation offers fine-grained control, targeted editing, and component reuse compared with direct video generation. This approach requires multimodal large language models (MLLMs)…
nlp
MMEnterprise-Bench: Evaluating Enterprise Agents over Evolving Multimodal Records
Enterprise agents answer questions over workplace records that evolve through team collaboration. As information is shared, corrected, and revised across documents, chats, and figures, multiple…
nlp
Omni-Woodpecker: Hallucination Correction via Evidence-Prior Rebalancing for Omni LLMs
Recent Omni LLMs (OLLMs) have demonstrated remarkable capabilities in joint audio-visual reasoning, yet cross-modal hallucinations remain a major challenge. Existing mitigation methods mainly operate…
nlp
AdaExploreBench: Benchmarking LLM Agents for Proactive Exploration and Test-time Adaptation in Evolving Environments
Large Language Model (LLM) agents are increasingly deployed in unfamiliar and evolving environments, requiring them to proactively explore, understand, and adapt to environmental dynamics. However,…
nlp
CoworkEnv: Synthesizing Training Environments for Long-Horizon Cowork Agents
AI coworkers must coordinate tools, communicate across turns, and act on changing workspace state while respecting workflow constraints. Constructing training experience for these capabilities…
nlp
Instruction Capacity: Behavior and Degradation of Language Models under Controlled Load
The quality with which language models follow instructions falls as the load grows, yet there is still no quantity that expresses the limit of a model in units of load with an uncertainty. We propose…
nlp