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
MLINFO COLLECTION
自然言語処理
記事一覧
14 / 44VibeVideoBench: Evaluating Multimodal Agents on Code-Driven Video Generation
Diffusion video models produce striking clips, but they cannot reliably render an exact formula, a correct chart, a rule-consistent game or narration synchronized to on-screen events. A different…
nlp
minimind — 🧠 Train a 64M-parameter LLM from scratch in just 2h!
このライブラリは、空間情報を扱うためのコンピュータビジョンライブラリです。
ジオメトリックなコンピュータビジョンライブラリ
awesome-MLSecOps — A curated list of MLSecOps tools and resources for securing machine learning and AI systems - adversarial ML defense, LLM security, AI red teaming, model scanning, supply-chain protection, and MLOps pipeline security.
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。
マルチモーダル理解技術の開発
ludwig — Low-code framework for building custom LLMs, neural networks, and other AI models
Ludwigは、LLM (Large Language Model) のカスタム化と構築のための低コストフレームワークです。このフレームワークは、ユーザーがカスタム LLM を構築し、トレーニングするのを容易にします。
LLMのカスタム化と構築のための低コストフレームワーク
Interpretable Feature Discovery from Unstructured Data Using LLMs and Statistical Choice Models
Feature extraction from unstructured data typically relies on opaque embeddings unsuited to interpretable decision-making. Interpretable features, on the other hand, typically require costly, and…
nlp
Toward Understanding the Value of Anarchy: Empirical Studies on Best Response Dynamics
We study experimental results of best response dynamics (BRD) in randomly generated weighted action networked multiagent optimization problems where agent utility is the agent's marginal contribution…
nlp
Efficacy of Monocular Depth Estimation in Lunar Environments
Recent advances in monocular depth estimation have demonstrated highly accurate 3D reconstructions within in-distribution terrestrial domains. This study investigates the efficacy of several…
nlp
From Error Prediction to Causal Influence: Auditing SAE Features in Multiple-Choice QA
Sparse autoencoders (SAEs) can predict internal features associated with model errors, but association alone does not establish causal influence. We study this distinction in multiple-choice question…
nlp
Conformal Predictive Distributions for Contextual Order Fulfillment Optimization
Ship-to-home fulfillment requires a retailer to select a fulfillment location and carrier before the delivery time is known. These decisions often rely on static transit-time estimates, which cannot…
nlp
Learning from Relative Action Credit for Escaping Local Minima
Reinforcement learning holds the promise of robots that learn manipulation skills from interaction alone, without pretrained priors or demonstration data. In practice, on-policy methods such as PPO…
nlp
Beyond Aggregate WER: In-domain Adaptation, Learner Speech, Code-Switching, and Speaker Attribution in Online Spanish Learning Classrooms
Automatic speech recognition (ASR) increasingly supplies transcripts for educational NLP, but aggregate word error rate (WER) can conceal errors concentrated in learner speech, multilingual turns,…
nlp
Measured or Real? When Model-Derived Measurements Can Be Corrected or Compared
Numbers computed from trained models, such as an example's difficulty or a model's benchmark lead, change with seed and prompt. We ask when such measurements can be corrected or compared.
nlp
Large Language Models for Accurate Medical Chart Abstraction: Enabling Scalable and Secure Artificial Intelligence Deployment in Stroke
Medical chart abstraction transforms unstructured clinical narratives into structured variables for research and quality monitoring. We evaluated a prompting-based large language model (LLM)…
nlp
"It Would Make a Geordie Feel at Home": Regional Accent Perceptions and Speech Accommodation in Voice AI
Automatic speech recognition (ASR) systems often perform less accurately for speakers of regional dialects, but less is known about how users respond to these limitations and how regional voices…
nlp
Self-Labeled Preference Transfer for Steerable Robot Manipulation
Vision-language-action (VLA) policies can learn to follow execution preferences, such as where to grasp an object or how to move around an obstacle, from demonstrations annotated with preference…
nlp
QMUL_AK at AISA-ArabicFC: Schema-Constrained Function Calling with ALLaM
We describe the QMUL_AK submission to AISA-ArabicFC 2026. The system adapts the Arabic-English ALLaM-7B-Instruct model to function calling with low-rank adaptation (LoRA).
nlp
SciGame: Let Agents Play the Scientific Discovery Games in the Real and Counterfactual World
Large language model agents are increasingly used for scientific discovery. However, existing benchmarks mix law inference with programming, score data fitting instead of prediction on unseen inputs,…
nlp
What Actually Matters? A Paired Evaluation of Inference Settings for $π_{0.5}$ on BEHAVIOR-1K
Vision-Language-Action (VLA) models offer a promising paradigm for general-purpose household robotics. However, inference and data-collection strategies that have been deployed in smaller-scale…
nlp
Beyond Utterance-Level Speaker Similarity: Perception-Aligned Segmental Evaluation of Accent in Speech Generation
Utterance-level similarity ratings do not reveal where perceived accent differences occur in generated speech. We introduce a segmental evaluation protocol combining speaker and accent similarity…
nlp
Multi-Agent Reinforcement Learning for Global Climate Policy Cooperation
International climate policy requires coordination among countries whose mitigation decisions impose local costs but generate global benefits. Classical game-theoretic and integrated assessment…
nlp
Human-Residual Steering: Aligning Frozen LLM Judges with Human Judgment Distributions
Large language models (LLMs) are widely used as automated judges, yet most alignment methods target aggregated human judgments and overlook variation among individual annotators. Existing approaches…
nlp
Finite-Sample Optimal Conformal Prediction Sets under Covariate Shift
We study conformal prediction under covariate shift with a known covariate density ratio, seeking prediction sets with minimum expected length under the target distribution. For every calibration…
nlp
Locating Sycophancy Across Training Stages in Open Language Models
Language model assistants sometimes change a correct answer when the user suggests a wrong one. The behavior, called sycophancy, is usually attributed to preference-based post-training, yet early…
nlp