Back to feed

research

143 posts

0
paperresearch14d

GRAN-TED: Generating Robust, Aligned, and Nuanced Text Embedding for Diffusion Models

0
0
paperresearch10d

CosineGate: Semantic Dynamic Routing via Cosine Incompatibility in Residual Networks

0
0
paperresearch9d

DiRL: An Efficient Post-Training Framework for Diffusion Language Models

0
0
paperresearch8d

Quantile Rendering: Efficiently Embedding High-dimensional Feature on 3D Gaussian Splatting

0
0
paperresearch8d

GateBreaker: Gate-Guided Attacks on Mixture-of-Expert LLMs

0
0
paperresearch8d

Shape of Thought: When Distribution Matters More than Correctness in Reasoning Tasks

0
0
paperresearch7d

UltraShape 1.0: High-Fidelity 3D Shape Generation via Scalable Geometric Refinement

0
0
paperresearch7d

Valori: A Deterministic Memory Substrate for AI Systems

0
0
paperresearch6d

Knot Forcing: Taming Autoregressive Video Diffusion Models for Real-time Infinite Interactive Portrait Animation

0
0
paperresearch5d

SpotEdit: Selective Region Editing in Diffusion Transformers

0
0
paperresearch5d

Introducing TrGLUE and SentiTurca: A Comprehensive Benchmark for Turkish General Language Understanding and Sentiment Analysis

0
0
paperresearch5d

VL-LN Bench: Towards Long-horizon Goal-oriented Navigation with Active Dialogs

0
0
paperresearch5d

Self-Evaluation Unlocks Any-Step Text-to-Image Generation

0
0
paperresearch5d

GraphLocator: Graph-guided Causal Reasoning for Issue Localization

0
0
paperresearch5d

DreamOmni3: Scribble-based Editing and Generation

0
0
paperresearch5d

Geometry-Aware Optimization for Respiratory Sound Classification: Enhancing Sensitivity with SAM-Optimized Audio Spectrogram Transformers

0
0
paperresearch4d

Dream-VL & Dream-VLA: Open Vision-Language and Vision-Language-Action Models with Diffusion Language Model Backbone

0
0
paperresearch4d

JavisGPT: A Unified Multi-modal LLM for Sounding-Video Comprehension and Generation

0
0
paperresearch3d

Reverse Personalization

0
0
paperresearch3d

SurgWorld: Learning Surgical Robot Policies from Videos via World Modeling

0
0
paperresearch3d

Evaluating Parameter Efficient Methods for RLVR

0
0
paperresearch3d

Bridging Your Imagination with Audio-Video Generation via a Unified Director

0
0
paperresearch3d

KernelEvolve: Scaling Agentic Kernel Coding for Heterogeneous AI Accelerators at Meta

0
0
paperresearch3d

YOLO-Master: MOE-Accelerated with Specialized Transformers for Enhanced Real-time Detection

0
0
paperresearch2d

Act2Goal: From World Model To General Goal-conditioned Policy

0
0
paperresearch2d

ProGuard: Towards Proactive Multimodal Safeguard

0
0
paperresearch2d

LiveTalk: Real-Time Multimodal Interactive Video Diffusion via Improved On-Policy Distillation

0
0
paperresearch2d

End-to-End Test-Time Training for Long Context

0
0
paperresearch2d

Robo-Dopamine: General Process Reward Modeling for High-Precision Robotic Manipulation

0
0
paperresearch2d

Stream-DiffVSR: Low-Latency Streamable Video Super-Resolution via Auto-Regressive Diffusion

0