This paper introduces a language-driven adaptive cost optimization framework for autonomous driving, leveraging GPT-4 to interpret natural language queries and adjust MPPI control parameters in real-time.

Diego Martinez-Baselga, Khaled Mustafa, Javier Alonso-Mora

Proposes WorldKernel, a positive semidefinite coupling kernel capturing unobserved cross-world dependencies, addressing prediction's inability to express counterfactual uncertainty.

Fabio Rovai

Pose-ICL enables pose-controllable subject customization with 3D-aware in-context learning, significantly improving pose accuracy and identity consistency.

Xuan Han, Yihao Zhao, Mingyu You

MV-Actor achieves 87.8% success by aligning multi-view semantics and spatial awareness.

Yinchen Tian, Huan Li, Muyao Peng et al.

KATE framework enhances LLM tool use by integrating experiential knowledge and expanding reasoning width, achieving a 15% improvement on BFCL-V3.

Yupu Hao, Zhuoran Jin, Huanxuan Liao et al.

Factorized spatio-temporal CNN combined with neural spline flow enables likelihood-free inference of stellar wind parameters from short noisy image sequences.

Niklas Knöll, Tobias Buck, Lorenzo Branca et al.

miniReranker employs visual cache reuse and interaction sparsity to reduce reranking runtime to <1% with >96% performance, based on Qwen3-VL.

Yingqi Fan, Xuan Lu, Anhao Zhao et al.

Predictor-gated bank-wise sparsity converts dense LLMs into 4× sparse models, improving long-text efficiency.

Ruixuan Huang, Jinyuan Shi, Hantao Huang et al.

REAL constructs a temporal, confidence-aware graph, boosting long-term memory by 22.72% in LLMs.

Keer Lu, Liwei Chen, Guoqing Jiang et al.

Proposes a multi-scale residual-aware framework combining Transformer models, achieving significant reduction in systematic bias for time series forecasting.

Amrijit Biswas, Mustafa Kamal, Robin Krambroeckers et al.

Proposes skill coverage metric based on trajectory detection of skill behavior constraints, achieving 38.66%-45.51% coverage; improves failed task recovery by 16%.

Boyin Tan, Xiaowei Huang, Youcheng Sun

VeriSpace employs dual-path 3D scene encoding and spatial reasoning to enhance action verification in VLA models, improving accuracy by 15% on benchmarks.

Guiyu Zhao, Longteng Guo, Junyou Zhu et al.

SkillAxe improves LLM skills by 28% through evaluation-guided self-refinement.

Srishti Gautam, Arjun Radhakrishna, Sumit Gulwani

GUI-AC enhances continual learning in GUI agents using Adaptive Advantage and Dynamic Clipping.

Can Lin, Tao Feng, Hangjie Yuan et al.

UniSVQ combines scalar and vector quantization via affine transforms, achieving near VQ performance with minimal storage overhead.

Haoyu Wang, Haiyan Zhao, Xingyu Yu et al.

Proposes high-temperature sampling to generate synthetic canaries for privacy auditing, improving detection of model memorization.

Nicole Mitchell, Galen Andrew, Arun Ganesh et al.

Trace2Policy transforms expert behavior into self-evolving decision agents using EISR, achieving 79.6% accuracy.

Junli Zha, Jinbo Wang, Chao Zhou et al.

Introduces SkillResolve-Bench and SkillResolve, achieving Recall@3 0.766, NDCG@3 0.699, and HSR@3=0, effectively reducing same-capability ambiguity risks.

Jiandong Ding

Proposed Adaptive Regime Routing (ARR) to address LLM knowledge conflicts, improving resistance EM from 6 to 16-33.

Runze Jiang, Taiqiang Wu, Yan Wang et al.

Proposes OWDiff, a wavelet diffusion framework, improving PSNR by 0.58dB for low-light images.

Fen Peng, Taizo Suzuki, Seisuke Kyochi