HiSkill enhances LLM agents with hierarchical skill graphs, achieving a 17.33% success rate increase and 78.75% reduction in inference token consumption.

Yu Hao, Jinxuan Cai, Qi Zhang et al.

Using a video transformer encoder, the study explores concept bottleneck models in echocardiography, finding volume supervision reduces errors.

Hyunkyung Han, Min Jung Kim

Using a diffusion-based generative framework for urban air quality reconstruction from sparse observations, achieving high performance on Paris dataset.

Abhishek A. Sabnis, Mihai Mitrea, Lya Lugon et al.

Proposes a human-in-the-loop workflow using SciSummNet and GPT-4o-mini for scientific summary simplification, with expert editing to preserve terminology and claims.

Kyuri Im, Michael Färber

MemSFT uses external parametric memory to mitigate alignment tax, boosting domain performance with minimal impact on general skills.

Jiarui Wang, Xiang Shi, Jiaqi Cao et al.

CORF-GS achieves real-time wireless radiance field (WRF) reconstruction via coupled optical-RF Gaussian optimization, with a 6.4× speedup.

Jinya Zhang, Jiajia Guo, Chao-Kai Wen et al.

Argus-Unified leverages pretrained VLM with hybrid tokens, achieving SOTA multimodal understanding and competitive generation at $2000 and 15.6M data.

Weiming Zhuang, Jiabo Huang, Jingtao Li et al.

I2VShield uses generative adversarial attacks to protect privacy, reducing computational costs and enhancing DiT model defenses.

Yimao Guo, Zuomin Qu, Wei Lu

TRWH combines LLM-generated text features with heterogeneous graphs via random walks, boosting sparse recommendation accuracy.

He Ma, Chen Liu

ODYSSE optimizes personalized reasoning via ESPO, enhancing long-horizon interaction tasks.

Jiaqi Zhang, Tong Chen, Junliang Yu et al.

CLBench-V evaluates multimodal context learning; best model scores only 0.2847.

Lai Wei, Chengqi Li, Jiapeng Li et al.

Proposes an instruction-free alignment approach for audio-language models, training only a lightweight projector, achieving performance comparable to heavily fine-tuned models.

Xuanru Zhou, Yiwen Shao, Jiahong Li et al.

Reproduction and extension of contrastive decoding (CD) reveal its effects are mainly due to distribution shifts, not true hallucination mitigation, across multiple models and datasets.

Arnav Bendre, Guneesh Gupta, Kavish Grover et al.

PreDiff-LM employs hybrid attention, combining pretrained causal transformers with bidirectional denoising, reducing perplexity from 34.1 to 28.7 on WikiText-103.

Zhengtao Yao, Runhao Li, Xupeng Chen et al.

Using ordinal pattern analysis and information-theoretic measures, the study achieves 99% accuracy in classifying 14 Peruvian news sources based on structural features.

Cynthia Z. Zhou-Lin, José L. Herrera-Diestra, Luciano Stucchi

PerceptionBench evaluates atomic visual perception in MLLMs; highest accuracy among 16 models is only 59.7%.

Zichao Lin, Yifeng Xie, Bowen Qu et al.

Mage-VL employs Codec-native sparse token encoding, reducing 75% tokens and achieving 3.5× inference speedup for real-time multimodal streaming.

Senqiao Yang, Kaichen Zhang, Zhaoyang Jia et al.

Proposes AUC of Pareto frontier for efficiency evaluation; introduces fluid search, outperforming fixed strategies in 12 tasks.

Haiqian Yang, Yuan Cao

PARED employs inverse RL in feature space to extract implicit rewards from demonstrations, improving language model alignment without task-specific annotations.

Michał Wiliński, Liu Leqi, Chirag Nagpal

CameraAnything integrates pixel-level Plücker rays and resolution-aware 3D RoPE in a diffusion framework for joint camera parameter control, supporting viewpoint, focal length, and resolution adjustments.

Yixuan Li, Yanhong Zeng, Ka Leong Cheng et al.