nestia — NestJS Helper + AI Chatbot Development
NestJSベースのAIチャットボット開発ツールです。
AIチャットボット作成
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
120 / 125caire — Content aware image resize library
Content aware image resize library
computer-vision
OpenWorldLib — Unified Codebase for Advanced World Models.
OpenWorldLibは、進化する世界モデルを提供する統一されたコードベースです。
世界モデルを提供する
Toward Contrast-Free Breast MRI: Improving Cancer Detection With Virtual Contrast Enhanced Imaging
Although contrast-enhanced (CE) breast MRI is an important tool for cancer detection, intravenous gadolinium administration introduces additional considerations for patients and clinical workflows.…
reinforcement-learning
Grounding Image Composition with Label-Conditioned Visual Evidence
Image composition labels such as center, diagonal, or rule of thirds describe visual structure rather than object categories. KU-PCP provides image-level labels and class-specific geometric elements,…
nlp
EDU-Jev Training System-One Decision Models for Education
Many automated decisions in education involve choosing from a fixed set of options: assigning a rubric score, checking whether an answer meets a marking criterion, or identifying the first wrong step…
nlp
Where, When, and How Many Bits? Scaling Laws for SGD with Stochastic Rounding
Low-precision training reduces computation but introduces additional rounding error. We theoretically study how stochastic rounding (SR) affects prediction risk as model size, training time, and…
deep-learning
Single-Annotation, Multi-Hypothesis Segmentation with Semantic-Spatial Residual Banks
Multi-rater segmentation datasets show that a single image can admit several valid masks, yet most training sets expose only one annotation per image. We study single-annotation multi-hypothesis…
nlp
Segment Anything Pancreas: A Unified MRI Segmentation Model for Pancreatic Cancer Radiotherapy
Background: Limited tumor annotations and incomplete labels across MRI datasets hinder unified segmentation of pancreatic tumors and organs at risk (OARs) for MRI-guided radiotherapy. Purpose: We…
deep-learning
Veloxity: Towards Memory-Safe UAV Embedded Firmware using the Rust Programming Language
Recent years have witnessed increased momentum towards memory-safe programming languages for safety-critical systems. Memory-safe languages can eliminate entire classes of common software errors that…
nlp
Consensus Within, Competition Between: Decentralized LLM Teams for Perimeter Defense
The use of large language models (LLMs) to coordinate multi-agent teams raises a fundamental architectural question: whether task allocation should be centralized in a single LLM controller or…
nlp
Capability-Grounded Agentic Planning
LLM agents serve natural-language requests through tools, data sources, and other agents, and even simple requests often need several interdependent calls. Typically, the LLM picks these calls by…
nlp
WebOverlay: High-Throughput Vision-Only Distillation for Extreme Aspect-Ratio Web Overlay Detection
Web overlays, such as cookie consent banners, newsletter prompts, and age gates, obstruct automated web crawlers and degrade downstream document representations. While proprietary multimodal Large…
deep-learning
Dreams Are Cheaper Than Flights: Curated World-Model Data Improves Aerial Detection
Robot perception is increasingly data driven, yet field data is slow, costly, and sometimes disruptive to collect. Video world models offer a cheaper source: seeded with real frames, they extend a…
computer-vision
Contact Imitation Interface: Transferring Dexterous Skills by Showing How Contact Unfolds
Robot-free human demonstrations offer a promising route to scaling dexterous manipulation data. The key challenge is to preserve the demonstrator's natural dexterity while producing contact-grounded…
reinforcement-learning
Omniprediction for All Mixable Proper Losses and Beyond
Omniprediction concerns the task of making predictions that are simultaneously accurate with respect to different losses. Earlier results by [CV09] show that in an online learning setting,…
machine-learning
Density-Guided Bootstrap Boundaries for Latent World-Model Reinforcement Learning
Latent world models allow reinforcement learning agents to learn policies from imagined trajectories, yet determining the optimal depth of model reliance remains a fundamental challenge. Fixed…
nlp
CuPIQP: A Batched and Differentiable QP Solver on GPUs for Robot Learning and Control
Quadratic programs (QPs) are fundamental building blocks of many robotic tasks such as inverse kinematics, whole-body control, and model predictive control. Extending these methods to large-scale…
deep-learning
Do Language Models Know What Compelling Scientific Evidence Looks Like?
Expert scientists excel at weighing empirical findings from multiple sources that vary in both statistical reliability and epistemic relevance. To what extent are language models, which are…
deep-learning
Language Models Show Conformity Bias in RAG: When the Majority Endorses a Poisoned Claim
Retrieval-augmented generation (RAG) can expose language models to misleading evidence in retrieved documents. We investigate whether increasing the number of mutually agreeing poisoned documents…
nlp
Prior-Guided Single-Exposure HDR Novel View Synthesis via Base-Gain Representation
Single-exposure high dynamic range (HDR) novel view synthesis (NVS) recovers HDR scenes from low dynamic range (LDR) views captured at a single exposure and estimates camera response function (CRF)…
computer-vision
STAR: Steering Action Representations during Inference
Vision-language-action models (VLAs) map language instructions and visual observations to robot actions, showing strong capabilities across robotic manipulation tasks. However, in our probing…
nlp
MOSAIC: Addressing Disproportionate Task-Modality Dependencies via Modality-Partitioned Gradient Routing
In multi-task settings, combining multiple modalities allows task representations to draw on signals that a single modality alone would not capture. However, individual tasks may depend…
deep-learning
Do Open Language Models Invent Scripture? BILAL-BENCH: Benchmarking Islamic-Source Fabrication in Bengali
When a language model invents a Qur'anic verse or hadith, it gives false authority to text that readers may treat as sacred. Existing Islamic hallucination benchmarks are largely Arabic and often…
nlp