SFD asynchronously denoises semantics ahead of texture, reaching FID 1.04 on ImageNet 256×256 and accelerating convergence up to 100×.

Yueming Pan, Ruoyu Feng, Qi Dai et al.

LineAR compresses KV cache for efficient autoregressive image generation, reducing ImageNet FID from 2.77 to 2.68.

Ziran Qin, Youru Lv, Mingbao Lin et al.

COOPER integrates depth and segmentation modalities, achieving 6.91% improvement in spatial reasoning via a two-stage training framework.

Zefeng Zhang, Xiangzhao Hao, Hengzhu Tang et al.

Proposes Soft Q-based Diffusion Fine-Tuning (SQDF), integrating KL regularization to enhance target reward and diversity in text-to-image generation.

Hyeongyu Kang, Jaewoo Lee, Woocheol Shin et al.

dVLM-AD enhances autonomous driving with diffusion VLM, achieving 9% improvement in behavior-trajectory consistency on WOD-E2E long-tail scenarios.

Yingzi Ma, Yulong Cao, Wenhao Ding et al.

MD-SNN improves quantized SNN accuracy via membrane potential distillation, achieving 14.85X energy efficiency boost.

Donghyun Lee, Abhishek Moitra, Youngeun Kim et al.

ResponsibleRobotBench evaluates robot responsibility in risk environments using multimodal LLMs with 85% success rate.

Lei Zhang, Ju Dong, Kaixin Bai et al.

Proposes KiMoI, a motion basis manipulation framework, to detect deepfake videos with subtle kinematic inconsistencies, improving generalization.

Alejandro Cobo, Roberto Valle, José Miguel Buenaposada et al.

PosterCopilot employs a three-stage training framework—PSFT, RL-VRA, RLAF—to improve layout accuracy and aesthetics, enabling layer-controlled iterative editing with high fidelity.

Jiazhe Wei, Ken Li, Tianyu Lao et al.

RELIC combines long-horizon memory with real-time streaming using compressed latent tokens, enabling interactive long-duration video world modeling at 16 FPS.

Yicong Hong, Yiqun Mei, Chongjian Ge et al.

Proposes test-time scaling with text embedding perturbation to boost diversity and quality in T2I diffusion models.

Hang Xu, Linjiang Huang, Feng Zhao

Proposes a training-free activation-space whitening method for policy violation detection, achieving 86.0% F1 score, outperforming fine-tuned baselines by up to 9.1 points.

Oren Rachmil, Avishag Shapira, Roy Betser et al.

MemVerse combines hierarchical knowledge graphs with parametric memory, enhancing multimodal lifelong learning with superior scalability.

Junming Liu, Yifei Sun, Weihua Cheng et al.

LAMP uses large language models for controllable video generation, enhancing motion control and user intent alignment.

Muhammed Burak Kizil, Enes Sanli, Niloy J. Mitra et al.

CrowdLLM integrates pretrained LLMs with generative models to create diverse, realistic virtual populations for social simulations and decision tasks.

Ryan Feng Lin, Keyu Tian, Hanming Zheng et al.

This study analyzes how preference distribution definitions (hard, soft, goal shaping) impact active inference agent performance in grid navigation.

Filippo Torresan, Ryota Kanai, Manuel Baltieri

Thucy employs a multi-agent architecture with LLMs to verify claims across multiple relational databases, achieving 94.3% accuracy on TabFact.

Michael Theologitis, Dan Suciu

ASCIIBench evaluates multimodal models' spatial reasoning via ASCII art, revealing significant representation bottlenecks.

Kerry Luo, Michael Fu, Joshua Peguero et al.

OneThinker unifies image and video reasoning across 10 tasks, trained on 600k data, with EMA-GRPO balancing rewards, achieving state-of-the-art results.

Kaituo Feng, Manyuan Zhang, Hongyu Li et al.

PPTArena benchmarks PowerPoint editing; PPTPilot, a structure-aware agent, surpasses VLMs by over 10% in complex, layout-sensitive tasks.

Michael Ofengenden, Yunze Man, Ziqi Pang et al.