Submitted by LXT 45 Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis · 9 authors 2
Submitted by tnlin 36 StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization · 10 authors 2
Submitted by yangbai123 34 From Generalist to Specialist: Adapting Vision Language Models via Task-Specific Visual Instruction Tuning · 6 authors 2
Submitted by ruizhaocv 18 EvolveDirector: Approaching Advanced Text-to-Image Generation with Large Vision-Language Models · 11 authors 2
Submitted by bczhou 17 Multi-Agent Collaborative Data Selection for Efficient LLM Pretraining · 11 authors 2
Submitted by ZenMoore 16 PositionID: LLMs can Control Lengths, Copy and Paste with Explicit Positional Awareness · 7 authors 2
Submitted by Lingaaaaaaa 16 SuperCorrect: Supervising and Correcting Language Models with Error-Driven Insights · 7 authors 3
Submitted by Lingaaaaaaa 12 Semantic Score Distillation Sampling for Compositional Text-to-3D Generation · 7 authors 2
Submitted by AaronXyl 8 Think While You Generate: Discrete Diffusion with Planned Denoising · 7 authors 3
Submitted by lefreud 7 ZeroComp: Zero-shot Object Compositing from Image Intrinsics via Diffusion · 5 authors 3
Submitted by RuoyiDu 5 I-Max: Maximize the Resolution Potential of Pre-trained Rectified Flow Transformers with Projected Flow · 7 authors 2
Submitted by JustinWong8314 4 SimpleStrat: Diversifying Language Model Generation with Stratification · 5 authors 2
Submitted by nokomon 4 Mentor-KD: Making Small Language Models Better Multi-step Reasoners · 3 authors 2
Submitted by lx865712528 4 DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models · 11 authors 3
Submitted by bangan 3 GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-time Alignment · 7 authors 2
Submitted by Purushothamann 1 Synth-SONAR: Sonar Image Synthesis with Enhanced Diversity and Realism via Dual Diffusion Models and GPT Prompting · 3 authors 2