Paper Reviews by AI

InfU: A new framework for flexible photo re-creation while preserving identity using Diffusion Transformers(DiTs).

Coarse-to-Fine Token Prediction improves autoregressive image generation by assigning the same coarse label for similar tokens, balancing generation quality and computational efficiency.

GFS-VL: Enhancing few-shot 3D segmentation by synergizing vision-language models with few-shot learning for robust real-world application.

Fin-R1: Financial reasoning via RL.

Expert Race: A flexible routing strategy for scaling diffusion transformer with mixture of experts.

New dataset bridges fabricated claims with humor for spotting online deception!

CLS-RL: Rule-based RL tackles catastrophic forgetting in MLLM image classification, outperforming SFT with better generalization and efficiency.

CaKE: Editing LLMs to Enhance Knowledge Generalization Across Reasoning Tasks.

TokenBridge bridges continuous and discrete tokens for autoregressive visual generation, achieving high-quality synthesis with simple autoregressive modeling.

AIMI: A system leveraging future knowledge & personalized data for accurate treatment adherence forecasting, paving the way for timely mobile interventions.

4DGS-1K: Achieves 1000+ FPS for dynamic scene rendering via a compact, memory-efficient framework, offering a 41x storage reduction and 9x faster speed.

TULIP enhances image-text pretraining by unifying generative data augmentation with contrastive learning, achieving state-of-the-art performance in visual understanding.

UAE-3D: A unified latent space approach for efficient & high-quality 3D molecular generation, outperforming existing methods in accuracy and speed.

FluxFlow: Make your video generator stronger via temporal regularization!

FakeVLM: A multimodal model & artifact-annotated dataset for detecting synthetic images with interpretable explanations, setting a new benchmark.

MotionStreamer: Streaming motion generation w/ diffusion-based autoregressive model in causal latent space.

LEGION: Grounding and explaining synthetic image detection and refinement via multimodal learning.

ELTEX: Domain-driven synthetic data generation framework improves LLM performance in cybersecurity with less resources.

Personalize diffusion models efficiently on devices without backpropagation.

DeepMesh: RL-guided auto-regressive creation of artist-quality 3D meshes, enhanced by tokenization & DPO for human-aligned aesthetics.