A Broader Look into MLLM's Retrieval Heads
Locating relevant evidence in long inputs is a core capability of Multimodal Large Language Models. Prior studies attribute this capability to retrieval heads, a sparse set of attention heads that…
nlp
MLINFO COLLECTION
自然言語処理
記事一覧
20 / 44Trial by Trace: Benchmarking AI Agent Harnesses for Reliability and Failure Attribution
LLM agents are increasingly used to solve real-world problems, and their effectiveness depends on both the underlying models and the harnesses that support their operation. However, most existing…
nlp
RSIHub: A Composable Framework for Agent-Evolution Methods
Agent-evolution methods use execution feedback to improve prompts, skills, tools, and orchestration, but their implementations often rebuild the same experimental machinery. We present RSIHub, an…
nlp
Principia: Test-Time Hypotheses to Principle Construction for Scientific Discovery
Scientific discovery requires identifying the scientific principles underlying observed phenomena to guide further investigation. As these empirical principles are often unknown in complex discovery…
nlp
CRM-Agent-Bench: Benchmarking Tool-Using Agents in Stateful Enterprise Environments
Deploying language agents in real applications demands more than the right answer: an agent must execute a multi-step business process correctly, follow domain-specific rules, and interact with a…
nlp
Sensorimotor Alignment: A Platonic Proxy for Embodied Policy Success
Robot foundation models are typically evaluated through costly closed-loop rollouts, motivating low-cost offline proxies for model capability. The Platonic Representation Hypothesis (PRH) suggests…
nlp
OmniSpectra: A Unified Foundation Model for Universal Spectra Representation Learning
Standard sequence models encode position by token rank rather than physical coordinate, typically forcing practitioners to destructively resample continuous physical signals such as spectra observed…
nlp
testtimescaling.github.io — "what, how, where, and how well? a survey on test-time scaling in large language models" repository
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。
大規模言語モデルのテスト時間調整
modelscope — ModelScope: bring the notion of Model-as-a-Service to life.
ModelScopeは、モデルをサービス化するためのプラットフォームです。モデルを作成し、ホスティングし、管理し、配信することができます。
モデルをサービス化する
Blind Random Search with Noisy Measurements: Almost Sure Convergence and Convergence Rates
Blind random search is a simple global optimization method that only requires the value of the loss function, without needing gradient information or an explicit loss model. However, its classical…
nlp
Generalization properties of the token perceptron: the role of embedding and vocabulary
Large language models are trained to predict tokens from a finite vocabulary, each represented by a vector in a $d$-dimensional embedding space. Therefore, token prediction is a classification…
nlp
Batched NN 4D-Var: a performant hybrid model framework for the Integrated Forecasting System
Hybrid forecasting systems combining machine learning and numerical weather prediction offer a promising route toward improved forecast skill while preserving physical consistency. In this study, we…
nlp
Random Jump Forests
Random jump forests are introduced as a nonparametric tool for estimating conditional cumulative transition rates and occupation probabilities in multi-state models. The main idea is that a single…
nlp
Data Quality Audit and Bivariate Temperature-Humidity Analysis of a Long-Term LoRaWAN Network: Anomaly Detection, PCA, Clustering and Machine Learning
Long-term environmental IoT/LPWAN deployments often aggregate heterogeneous data streams from diverse devices without systematic auditing of each variable's actual coverage prior to analysis-an…
nlp
Searching with Sparse Histories: Cross-Task Architecture Search from Incomplete Search Logs and Zero-Cost Proxies
Neural architecture search (NAS) is expensive, but cross-task transfer can reduce costs by reusing knowledge from previous tasks. However, existing methods struggle with sparse search histories and…
nlp
Implicit Neural Representations for Variational Problems on Graphons
We propose a neural exploratory framework for variational problems over graphons, i.e., symmetric measurable functions $[0,1]^2 \to [0,1]$, that arise as limits of dense graph sequences. Such…
nlp
Conditional Flow Models for Offline Maximum Entropy Reinforcement Learning
Offline maximum entropy reinforcement learning seeks to estimate the optimal soft action-value function \(Q^*\) from a fixed dataset without further interaction with the environment. Although \(Q^*\)…
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
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
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
PaperFormalizer: Author-in-the-Loop Autoformalization of Research Papers in Lean
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…
nlp
FLORA: An Open Model Suite for Scaling Robotics Data Engines
The life-cycle of robotics foundation models crucially depends on data labels. Outcome reward labels are needed for monitoring real-world deployments.
nlp
DirCast: 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
FocusVLA: Future-Intent Guided Dynamic View Routing for Vision-Language-Action Models
Vision-language-action (VLA) models have become an important paradigm for robotic manipulation by unifying visual perception, language understanding, and action generation. Since reliable…
nlp