Proposed a two-stage deep learning framework using YOLOv8n and RexNet-150, achieving 95% accuracy in cheating detection.

Van-Truong Le, Le-Khanh Nguyen, Trong-Doanh Nguyen

DENALI dataset enables non-line-of-sight spatial reasoning with low-cost LiDARs, covering 72,000 scenes.

Nikhil Behari, Diego Rivero, Luke Apostolides et al.

This paper introduces complete cyclic subtask graphs for long-horizon LLM tool agents, analyzing flexibility, costs, and bottlenecks.

Luay Gharzeddine, Samer Saab

Proposes two uncoupled algorithms achieving last-iterate convergence at rate Ω(T^{-1/4}) in bandit feedback zero-sum games.

Côme Fiegel, Pierre Ménard, Tadashi Kozuno et al.

Prototype-Grounded Concept Models (PGCMs) verify concept alignment via visual prototypes, enhancing interpretability.

Stefano Colamonaco, David Debot, Pietro Barbiero et al.

MemExplorer enhances energy efficiency by up to 2.3x in heterogeneous memory design.

Haoran Wu, Zeyu Cao, Yao Lai et al.

Combining convolution and delay learning in RSNNs achieves 52x inference speedup and 99% parameter savings on audio tasks.

Lúcio Folly Sanches Zebendo, Eleonora Cicciarella, Michele Rossi

SENSE leverages stereo vision and vision-language models to enhance open-vocabulary semantic segmentation, achieving a 2.9% precision improvement on PhraseStereo.

Thomas Campagnolo, Ezio Malis, Philippe Martinet et al.

Proposed a fleet sizing rule for multi-UAV missions ensuring 99.8% success, needing only four extra drones even under harshest conditions.

Vishal Ramesh, Antony Thomas

DTEA enables real-time switching between SEA and PEA topologies with switching time under 33.33 ms.

Vishal Ramesh, Aman Singh, Shishir Kolathaya

Proposed environment-adaptive solid-state LiDAR-inertial odometry, achieving 12.8% average RMSE reduction.

Zhi Zhang, Chalermchon Satirapod, Bingtao Ma et al.

In modular robots, Lamarckian evolution outperforms Darwinian in single-task optimization but declines under morphological diversity pressure.

Jed R Muff, Karine Miras, A. E. Eiben

DepCap uses cross-step dependency and conflict-aware decoding, reaching up to 5.63× speedup with negligible quality loss.

Xiang Xia, Wuyang Zhang, Jiazheng Liu et al.

Neuromorphic parameter estimation for power converter health monitoring using spiking neural networks, achieving ~270x energy reduction.

Hyeongmeen Baik, Hamed Poursiami, Maryam Parsa et al.

Introduces OVRSISBenchV2 and Pi-Seg, expanding to 95K images for robust open-vocabulary remote sensing segmentation.

Bingyu Li, Tao Huo, Haocheng Dong et al.

AdaDINO uses task-adaptive NAS to improve edge vision models, boosting accuracy by 7.9% and reducing FLOPs by 74.9%.

Yiwei Zhao, Yi Zheng, Huapeng Su et al.

Self-distillation reduces fine-tuning-induced hallucinations, lowering factual forgetting from 15% to 3%.

Guy Kaplan, Zorik Gekhman, Zhen Zhu et al.

ShapeGen generates diverse shape manipulation data to enhance policy category-level generalizability.

Yirui Wang, Xiuwei Xu, Angyuan Ma et al.

Proposes ordered 1D tokens for efficient test-time search in autoregressive image generation, improving scalability and quality.

Zhitong Gao, Parham Rezaei, Ali Cy et al.

Bi-CMPStereo framework significantly improves accuracy and generalization in event-frame asymmetric stereo matching.

Ninghui Xu, Fabio Tosi, Lihui Wang et al.