KI-Forschungspapiere Täglich

WildGS-SLAM: Monocular Gaussian Splatting SLAM in Dynamic Environments

Are We Done with Object-Centric Learning?

DiTaiListener: Controllable High Fidelity Listener Video Generation with Diffusion

Missing Premise exacerbates Overthinking: Are Reasoning Models losing Critical Thinking Skill?

OmniCaptioner: One Captioner to Rule Them All

RobustDexGrasp: Robust Dexterous Grasping of General Objects from Single-view Perception

A Unified Agentic Framework for Evaluating Conditional Image Generation

Fast Controlled Generation from Language Models with Adaptive Weighted Rejection Sampling

DDT: Decoupled Diffusion Transformer

Self-Steering Language Models

A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibility

Pretraining Language Models for Diachronic Linguistic Change Discovery

GenDoP: Auto-regressive Camera Trajectory Generation as a Director of Photography

VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning

RuOpinionNE-2024: Extraction of Opinion Tuples from Russian News Texts

Caption Anything in Video: Fine-grained Object-centric Captioning via Spatiotemporal Multimodal Prompting

Masked Scene Modeling: Narrowing the Gap Between Supervised and Self-Supervised Learning in 3D Scene Understanding

FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesis

OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens

SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills