KOINEU

Feedforward 3D Editing via Text-Steerable Image-to-3D

: Steer3D는 이미 훈련된 이미지 투 3D 생성 모델에 텍스트 가이드 기능을 추가하여, 3D 자산을 편집할 수 있게 합니다. ControlNet의 아키텍처를 활용하여 이미지 투 3D 사전 학습에서 얻은 모양과 객체 우선순위를 이용합니다. 또한 자동 데이터 엔진을 구축하여 다양한 기하학적 및 질감 편집 쌍을 생성하고, 두 단계 훈련 레시피를 통해 흐름 일치 훈련과 직접 선호도 최적화를 통합합니다. Steer3D는 언어 지시를 잘 따르고 원래 3D 자산과의 일관성을 유지하면서도 매우 빠른 속도를 보여줍니다.

Feedforward 3D Editing via Text-Steerable Image-to-3D

FIBER: A Multilingual Evaluation Resource for Factual Inference Bias

FineSkiing: A Fine-grained Benchmark for Skiing Action Quality Assessment

Fraud Detection Through Large-Scale Graph Clustering with Heterogeneous Link Transformation

GCoDE: Efficient Device-Edge Co-Inference for GNNs via Architecture-Mapping Co-Search

GHOST: Solving the Traveling Salesman Problem on Graphs of Convex Sets

ICP-4D: Bridging Iterative Closest Point and LiDAR Panoptic Segmentation

Irresponsible AI: big tech's influence on AI research and associated impacts

Learned-Rule-Augmented Large Language Model Evaluators

Learning to Code with Context: A Study-Based Approach

LeMiCa: Lexicographic Minimax Path Caching for Efficient Diffusion-Based Video Generation

LiveTradeBench: Seeking Real-World Alpha with Large Language Models

LUME-DBN: Full Bayesian Learning of DBNs from Incomplete data in Intensive Care

Moral Susceptibility and Robustness under Persona Role-Play in Large Language Models

Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

Not All Instances Are Equally Valuable: Towards Influence-Weighted Dataset Distillation

Online Expectation-Maximisation

PACIFIC: a framework for generating benchmarks to check Precise Automatically Checked Instruction Following In Code

PaTaRM: Bridging Pairwise and Pointwise Signals via Preference-Aware Task-Adaptive Reward Modeling

PhysWorld: From Real Videos to World Models of Deformable Objects via Physics-Aware Demonstration Synthesis

Policy Gradient-Based EMT-in-the-Loop Learning to Mitigate Sub-Synchronous Control Interactions

Prudential Reliability of Large Language Models in Reinsurance: Governance, Assurance, and Capital Efficiency

Quadratic Direct Forecast for Training Multi-Step Time-Series Forecast Models

Quality Assurance of LLM-generated Code: Addressing Non-Functional Quality Characteristics

Reconfigurable Quantum Instruction Set Computers for High Performance Attainable on Hardware

RGE-GCN: Recursive Gene Elimination with Graph Convolutional Networks for RNA-seq based Early Cancer Detection

Supervised Fine-Tuning or In-Context Learning? Evaluating LLMs for Clinical NER

SymLight: Exploring Interpretable and Deployable Symbolic Policies for Traffic Signal Control

The FM Agent

The Geometric View of Theories

The Hidden Cost of Straight Lines: Quantifying Misallocation Risk in Voronoi-based Service Area Models

Uncovering Competency Gaps in Large Language Models and Their Benchmarks

VFocus: Better Verilog Generation from Large Language Model via Focused Reasoning

A Memory-Efficient Retrieval Architecture for RAG-Enabled Wearable Medical LLMs-Agents

A Unified Architecture for N-Dimensional Visualization and Simulation: 4D Implementation and Evaluation including Boolean Operations

Advancing Equitable AI: Evaluating Cultural Expressiveness in LLMs for Latin American Contexts

Conformal Prediction-Driven Adaptive Sampling for Digital Water Twins

Cultural Rights and the Rights to Development in the Age of AI: Implications for Global Human Rights Governance

Detecting Silent Failures in Multi-Agentic AI Trajectories

Discourse-Aware Scientific Paper Recommendation via QA-Style Summarization and Multi-Level Contrastive Learning

Endowing GPT-4 with a Humanoid Body: Building the Bridge Between Off-the-Shelf VLMs and the Physical World

Enhancing Interpretability for Vision Models via Shapley Value Optimization

EU-Agent-Bench: Measuring Illegal Behavior of LLM Agents Under EU Law

Explainable Adversarial-Robust Vision-Language-Action Model for Robotic Manipulation

Fine-Tuning LLMs to Generate Economical and Reliable Actions for the Power Grid

Fourier Neural Operators for Structural Dynamics Models: Challenges, Limitations and Advantages of Using a Spectrogram Loss

From Verification Burden to Trusted Collaboration: Design Goals for LLM-Assisted Literature Reviews

GAMA: A Neural Neighborhood Search Method with Graph-aware Multi-modal Attention for Vehicle Routing Problem

Group Interventions on Deep Networks for Causal Discovery in Subsystems

Heterogeneous Robot Collaboration in Unstructured Environments with Grounded Generative Intelligence

< Category Statistics (Total: 5502) >

Start searching

No results found