GeoDistill-Refine employs multi-prompt fusion and signed distance fields, boosting annotation-free spacecraft segmentation IoU by 4.56% and Boundary F1 by 13.80%.

Yonglong Zhang, Zongwu Xie, Yang Liu

DynaCrys: Crystal generation with dynamic space-group diffusion, enhancing novel crystal discovery rates.

Zhuotao Jin, Xiaoyun Wang, Nicholas Brawand et al.

FinRank leverages manually curated hard negatives to enhance financial QA evidence discrimination, with a benchmark of 1185 question-answer pairs.

Sasan Mansouri, Daniel Saad, Mark Wahrenburg et al.

This study introduces depth-wise probing and pruning of the planning token in a driving VLA model, revealing early linear decodability of semantic intent and enabling 1.33× speedup with minimal performance loss.

Harisankar Babu, Benjamin Coors, Christopher Lang et al.

Introduces quantum-inspired complex phase states, reducing training steps by ~3x, validated on byte-level text datasets with superior efficiency.

Ahmed Nebli, Hadi Saadatdoorabi, Christopher Keibel et al.

WNM-3D adds 3D scene tokens to closed-loop VLN; the supplied paper text reports gains on GN-Bench but omits exact scores.

Yuehao Huang, Yunzi Wu, Xiaotao Zhang et al.

CANIS uses a generation-assisted semantic bridge for category-agnostic 3D canonicalization, improving classification and segmentation performance.

Kendong Liu, Yuxin Yao, Junhui Hou

Momba enhances multi-objective RL by integrating SimbaV2 architecture with feature normalization, weight normalization, and distributional critic, achieving higher sample efficiency and better solution sets.

Adam Štafa, Santeri Heiskanen, Petr Novotný et al.

Modular TTT models test-time training as a composable graph, improving flexibility and efficiency in sequence modeling.

Bohao Tang, Zhen Qin, Yuqi Pan et al.

Introduces 'Readout-Rank Laws' describing how measurement restrictions cause geometric information loss in quantum systems, quantified by Beta distributions.

Marwan Ait Haddou

MemWM enhances text-based world models with memory, boosting SSF by up to 206.3% and success rate by 65.4% in multi-environment benchmarks.

Yujun Wang, Tao Zhang, Jinhe Bi et al.

PILOT framework uses representational deduction with Motion CoT to decouple high-level intention from low-level trajectories, achieving 97.9% success on LIBERO.

Xiangkai Ma, Yue Ma, Junjie Wang et al.

GPTKB 2.0 constructs a disambiguated knowledge base with 38.4 million triples, enabling traceable entity disambiguation using context-aware LLMs.

Yujia Hu, Tuan-Phong Nguyen, Simon Razniewski

DCMPC-Net uses cross-modal prompts for unified adverse-weather restoration, but the supplied text reports no numerical metrics.

Wanshu Fan, Yunzhe Zhang, Yue Shen et al.

Introduces MMAG benchmark with 4,000 annotated multi-domain audio clips, evaluating fidelity, semantic alignment, and temporal control, revealing performance trade-offs.

Zihao Zheng, Xuenan Xu, Jiahao Mei et al.

SkillEval learns interpretable linear directions in model embeddings to evaluate four skill document dimensions, correlating with downstream task performance.

Jiahui Han, Qinuo Li, Ziheng Peng et al.

StateFlow introduces sequence chunking with dependency-aware pipeline parallelism, achieving up to 2.22× throughput and 2.45× memory reduction for long-context models.

Wenxuan Zhao, Yingfa Chen, Xu Han et al.

FYI integrates AI and manual tools to enhance fact-checking efficiency for data-driven articles.

Nguyen-Truong Thinh, Yuxuan Du, Phongsakon Mark Konrad et al.

Proposes AgentChaos, a runtime, non-intrusive HTTP-layer fault injection framework to evaluate agent system robustness against 65 LLM API response faults.

Gou Tan, Zhensu Sun, Jieke Shi et al.

HSMLA combines multi-scale linear attention with content-aware sparse softmax, achieving 4× speedup with high accuracy in high-res vision tasks.

Dong Liu, Yanxuan Yu, Renata Borovica-Gajic et al.