How a group that cannot communicate knows itself by its enemy
Teams that cannot communicate seem stuck with what each member sees. We show that their opponent can tell them the rest.
reinforcement-learning
MLINFO COLLECTION
新着記事
日次更新の新着・公開記事を新しい順に掲載しています。
記事一覧
75 / 125Spatial Atlas-Informed Loss Ensembles for Whole-Body PSMA PET/CT Metastasis Segmentation
Existing whole-body PSMA PET/CT prostate metastasis segmentation methods generally rely on images alone, without explicitly incorporating where metastases tend to occur. We investigate whether a…
deep-learning
EgoHSI3R: Online 4D Hand-Scene Interaction Reconstruction from Egocentric Video
Egocentric videos offer an abundant source of hand-scene interactions for embodied learning, which requires recovering hands, camera, and scene consistently in a shared 3D world. Existing methods…
deep-learning
From Teleoperation to Long-Horizon Dexterity: Evaluating Visuomotor Skills and Offline Proxies for Dexterous Manipulation
Imitation learning policies are intended to make robotic manipulation robust to variations in object pose, appearance, and environment that challenge pre-programmed motion. However, real-world…
computer-vision
Drone-PUR: From Visual Clue Discovery to Understanding and Reasoning in UAV Scenes
The reasoning capabilities of vision-language models (VLMs) can be limited by incomplete or inaccurate visual observations in the general domain. In unmanned aerial vehicle (UAV) scenes, small…
nlp
CaPtain: A Pipeline for Post-Training Code-as-Policy Robot Agents
Across coding, web, and tool-use tasks, language-model agents are now routinely trained with the same recipe: supervised fine-tuning (SFT) to learn the interface, then multi-turn reinforcement…
nlp
AutoHebb: Self-Modifying Neural Networks that Zero-Shot Infer and Continually Learn
Humans and animals have a unique capacity to generalize and learn in novel circumstances, including "0-shot" inference (ZI) and continual learning (CL) -- two powerful cognitive abilities. Despite…
deep-learning
Safin-1.5: Safety-Native Architecture and Verifiable Reasoning for Recursive Safety Improvement
Recursive self-improvement (RSI) enables large language models to advance their capabilities through successive updates, but these updates can also introduce new risks and weaken existing safeguards.…
nlp
WorldBridge: Bridging Video and Action for Task Generalization in World Action Models
Achieving the broad task generalization of embodied models in physical environments remains a central challenge in robot learning. We study this challenge in World Action Models (WAMs) through two…
nlp
Mage-VL-Cowork: A Full Training Recipe to Learn Hybrid Computer Use From Evolved Harnesses
Effective computer-use agents (CUAs) should seamlessly combine visual GUI interaction with code and terminal execution within a single policy. We present Mage-VL-Cowork, a 4B hybrid CUA trained from…
deep-learning
Prevented is Not Protected: What Attack Success Rate Hides about RAG
Retrieval-Augmented Generation (RAG) is vulnerable to knowledge poisoning, where adversaries manipulate retrieved evidence to influence model outputs. Existing defenses are primarily evaluated using…
nlp
Certified Behavioral Retention for Continual Adaptation with Held-Out Anchors
Continual adaptation requires deciding not only how to update a model, but whether to commit an update without exceeding a declared budget for changes to protected behavior. We introduce Certified…
deep-learning
Apriel Voice 27B Preview: An Open Model for Speech, Reasoning, and Tool Use
A capable voice assistant must do more than recognize words; it must understand requests, reason over context, sustain conversations, and act through tools. We present Apriel Voice 27B Preview, an…
deep-learning
INLA for Adaptive UAV Sampling of Radio Environment Maps in IoT Networks: Prior Width Governs Accuracy and Calibration
We study adaptive UAV sampling for radio environment map (REM) construction from non-Gaussian IoT observations. Integrated nested Laplace approximation(INLA) updates a Matérn GMRF posterior, with…
deep-learning
The Geometry of Multitask Learning: Sharp Rates for Shared Subspace Estimation
Learning a shared subspace in multitask learning is an important statistical problem, yet exact rates remain poorly understood in many of the formal settings considered in the literature. To address…
machine-learning
Elucidating the Design Space of LM Data Attribution
Data attribution methods for Language Models (LMs) are typically evaluated using downstream tasks like fact retrieval. However, existing evaluations vary multiple dataset properties simultaneously,…
nlp
Propose-Filter-Release: Scaling Noise to Typical Sensitivity via Private Filtering
An estimator can be accurate and stable on typical data, yet sensitive to a few possible records. Differentially private mechanisms commonly scale their noise to the worst-case influence of a single…
deep-learning
Micro-Edits: Computational Support for Fine-Scale Edits in Film
In film editing, every frame matters. While macro, content-level edits shape the high-level narrative of a film, small local edits often control timing and direct visual attention.
deep-learning
Rethinking Neural Thickets Without Weight Perturbations
The Neural Thickets hypothesis posits that pretrained language models lie in dense neighborhoods of task-specific experts in weight space, which random Gaussian perturbations can uncover. We…
computer-vision
Read, Allocate, Route: Role-Coupled Tokenization for Pixel-Space Generative Transformers
Pixel-space generative Transformers typically use one token per image patch, so capturing finer detail requires more tokens and makes global attention increasingly expensive. We observe that finer…
deep-learning
SwapBot: Tool-Centric Robot Manipulation via Interchangeable End-Effectors and Tactile Sensing
Robot manipulation in everyday environments inherently involves substantial tool usage. Seemingly simple household tasks, such as cooking pan-fried tofu, require forceful cutting, delicate brushing,…
deep-learning
Adaptive Scenario Generation for KL-DRO Around a Learned Density Model
Distributionally robust optimization (DRO) hedges data-driven two-stage stochastic programs against error in the distribution estimated from a finite record, and standard ambiguity sets differ in how…
computer-vision
Luggage re-identification: A study of strategies towards a real-world application
Luggage re-identification (ReID) is a critical task in video surveillance for forensics, security or border management (suspicious or abandoned luggage recognition), as well as luggage management…
nlp
From extreme weather to agricultural consequences with agentic AI
Extreme weather is forecast days ahead, yet its consequences for agriculture remain hard to predict: a forecast says where a storm will strike, not which crops will suffer or how much is at risk, and…
computer-vision