AI Research Papers Daily

CoSTAast: Cost-Sensitive Toolpath Agent for Multi-turn Image Editing

Transformers without Normalization

World Modeling Makes a Better Planner: Dual Preference Optimization for Embodied Task Planning

Charting and Navigating Hugging Face's Model Atlas

Silent Branding Attack: Trigger-free Data Poisoning Attack on Text-to-Image Diffusion Models

CoRe^2: Collect, Reflect and Refine to Generate Better and Faster

GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and Editing

VisualPRM: An Effective Process Reward Model for Multimodal Reasoning

GroundingSuite: Measuring Complex Multi-Granular Pixel Grounding

New Trends for Modern Machine Translation with Large Reasoning Models

Shifting Long-Context LLMs Research from Input to Output

4D LangSplat: 4D Language Gaussian Splatting via Multimodal Large Language Models

OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal Inpainting

VisualWebInstruct: Scaling up Multimodal Instruction Data through Web Search

DiT-Air: Revisiting the Efficiency of Diffusion Model Architecture Design in Text to Image Generation

Open-Sora 2.0: Training a Commercial-Level Video Generation Model in $200k

Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond

Do I look like a `cat.n.01` to you? A Taxonomy Image Generation Benchmark

SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation

Distilling Diversity and Control in Diffusion Models

Long Context Tuning for Video Generation

UniGoal: Towards Universal Zero-shot Goal-oriented Navigation

R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization

CINEMA: Coherent Multi-Subject Video Generation via MLLM-Based Guidance

Quantization for OpenAI's Whisper Models: A Comparative Analysis

Communication-Efficient Language Model Training Scales Reliably and Robustly: Scaling Laws for DiLoCo

Autoregressive Image Generation with Randomized Parallel Decoding

The Curse of Conditions: Analyzing and Improving Optimal Transport for Conditional Flow-Based Generation

Discovering Influential Neuron Path in Vision Transformers

"Silent Is Not Actually Silent": An Investigation of Toxicity on Bug Report Discussion

ConsisLoRA: Enhancing Content and Style Consistency for LoRA-based Style Transfer

Piece it Together: Part-Based Concepting with IP-Priors

MinorBench: A hand-built benchmark for content-based risks for children

On the Limitations of Vision-Language Models in Understanding Image Transforms

PerCoV2: Improved Ultra-Low Bit-Rate Perceptual Image Compression with Implicit Hierarchical Masked Image Modeling

TruthPrInt: Mitigating LVLM Object Hallucination Via Latent Truthful-Guided Pre-Intervention