coDrawAgents framework improves compositional text-to-image generation with 94% overall accuracy on GenEval via multi-agent collaboration.

Chunhan Li, Qifeng Wu, Jia-Hui Pan et al.

NanoVDR distills a 2B vision-language retriever into a 70M text-only encoder for visual document retrieval, retaining 95.1% of teacher quality.

Zhuchenyang Liu, Yao Zhang, Yu Xiao

OARS framework uses COMPASS reward for real-time image super-resolution, enhancing perceptual quality and fidelity.

Shijie Zhao, Xuanyu Zhang, Bin Chen et al.

Proposed EISAM framework significantly boosts tail-item recommendation performance.

Jiaming Zhang, Yuyuan Li, Xiaohua Feng et al.

Proposed an SRAM-based CIM accelerator optimizing linear-decay SNNs, achieving 15.9 to 69 times energy efficiency improvement.

Hongyang Shang, Shuai Dong, Yahan Yang et al.

VecMol generates 3D molecules using vector-field representations, avoiding explicit graph generation and enhancing geometry-chemistry coherence.

Yuchen Hua, Xingang Peng, Jianzhu Ma et al.

AnchorRec prevents positional collapse in multimodal recommender systems using anchored alignment, enhancing recommendation accuracy.

Yonghun Jeong, David Yoon Suk Kang, Yeon-Chang Lee

FGTR achieves fine-grained multi-table retrieval via hierarchical LLM reasoning, improving F_2 by 18% on Spider and 21% on BIRD datasets.

Chaojie Sun, Bin Cao, Tiantian Li et al.

VGGT-World predicts scene geometry evolution via autoregressive modeling of frozen GFM features, achieving 21% better depth accuracy with 0.43B params, 3.6-5× faster.

Xiangyu Sun, Shijie Wang, Fengyi Zhang et al.

The paper refines and extends the batched kernelized bandits problem, optimizing batch numbers and regret bounds.

Chenkai Ma, Keqin Chen, Jonathan Scarlett

VLM4Rec enhances multimodal recommendation by leveraging large vision-language models for semantic representation.

Ty Valencia, Burak Barlas, Varun Singhal et al.

InterDeepResearch enables human-agent collaborative information seeking through an interactive deep research framework, enhancing process observability and real-time steerability.

Bo Pan, Lunke Pan, Yitao Zhou et al.

DeepCommit reconstructs verifiable Milestone DAGs for evaluating AI agents on continuous software evolution, revealing performance drops from 80% to 38%.03%.

Gangda Deng, Zhaoling Chen, Zhongming Yu et al.

TRACE combines knowledge graphs and LLMs for interpretable stock prediction, achieving 55.1% accuracy on S&P 500.

Qianggang Ding, Haochen Shi, Luis Castejón Lozano et al.

Using log-odds ratio analysis, this study reveals systematic biases in LLM-generated educational feedback conditioned on student attributes, highlighting overuse of praise and stereotype reinforcement.

Mei Tan, Lena Phalen, Dorottya Demszky

Introduces Alternating Gradient Flow (AGF) to prevent structural collapse under 75% compression on ImageNet-1K.

Tianhao Qian, Zhuoxuan Li, Jinde Cao et al.

MamTra combines Mamba and Transformer, reducing inference VRAM usage by 34% with only 2% training data.

Tan Dat Nguyen, Sangmin Bae, Joon Son Chung et al.

Study reveals three phases in fully-connected neural networks through dropout pruning: eumentia, dementia, and amentia.

Haining Pan, Nakul Aggarwal, J. H. Pixley

VQQA employs multi-agent QA with semantic gradients to improve video quality by +11.57%.

Yiwen Song, Tomas Pfister, Yale Song

EVATok achieves efficient visual autoregressive generation with adaptive video tokenization, saving 24.4% tokens on average.

Tianwei Xiong, Jun Hao Liew, Zilong Huang et al.