TurboBias 2.0 introduces case-insensitive GPU phrase boosting and multi-stream personalization, boosting recognition F-score to 87.5 with low latency.

Vladimir Bataev, Lilit Grigoryan, Andrei Andrusenko et al.

Proposes across-design uncertainty analysis using simulated price trajectories, decomposing estimation error into within-design and across-design components.

Pedro Cadahia Delgado

Trajectory-level framework analyzes 3,500 diagnostic paths, improving microservice root cause localization accuracy from 43.5% to 52.5% using fault propagation path validation.

Qisheng Lu, Aoyang Fang, Junjielong Xu et al.

SPARCL uses spectral partitioning to freeze high-energy directions, mitigating spectral interference in analytic continual learning.

James Hartley, Zeropy Surio, Daniel Whitmore et al.

Re3Cap employs retrieval-guided reasoning with k-core analysis to boost image captioning, achieving 8.64% improvement in relation reasoning on COCO-LN500.

Haonan Jia, Shichao Dong, Zenghui Sun et al.

This study systematically compares six fine-tuning strategies for MedSAM in OOD settings, revealing encoder LoRA enhances robustness by stabilizing decoder representations.

Marko Haralović, Sounic Akkaraju, Carlo Baretta et al.

AUSO unifies skill internalization and utilization via action-aware progressive reinforcement learning, improving long-horizon task performance.

Huizu Lin, Chengkai Huang, Tianqi Gao et al.

Difficulty-calibrated flow matching (DC-FM) dynamically adjusts interpolation paths based on model-measured learning difficulty, improving sample quality especially under resource constraints.

Airin Akter Tania, Md Raihan Khan

WildFin employs pre-trained vision models (DINOv3, VideoMAE, V-JEPA2) for fish behavior classification on 2 million frames, highlighting performance gaps in complex underwater scenes.

Abigail G. Grassick, Jerome Tze-Hou Hsu, Ethan Lin et al.

CLEAR uses input-conditioned latent gating to reduce HarmBench ASR from 32.3% to 0.5%, maintaining high utility on GSM8K and other tasks.

Chengxiao Wang, Enyi Jiang, Xiaojing Liao et al.

Introduces the Exceedance Design Effect to correct clustering bias in threshold-based conformal prediction, improving effective sample size estimates.

Adam Noonan

Few-shot fine-tuning on target domain surpasses unsupervised domain adaptation in cross-crop weed detection, with as few as 25 labeled samples.

Nikhilesh Prabhakar, Pranuthi Tenali, Wilfredo Abudeye Fernandez et al.

TRACE-C employs rank calibration and multi-channel residuals to detect joint anomalies in multistream telemetry data.

Matthew Faucher

GPU fine-grain parallelization of GPX partitioning accelerates large-scale TSP solving by 48-625×, reducing memory use significantly.

Swetha Varadarajan, Darrell Whitley

Proposed a new diffusion transformer architecture using static text anchors for efficient multi-reference image editing, achieving a 3.92x speedup.

Yangshuai Liu, Zheming Li, Jiaao Li et al.

Proposed PSL framework combines semi-structured political records' stance and structural signals, significantly improving predictive political QA.

Yinan Liu, Zihan Zhou, Zichun Jin et al.

Q-Planning integrates a frozen behavior cloning policy with a small off-policy Q-function, enabling stable self-improvement and success rates up to 99%.

Varun Giridhar, Anant Khandelwal, Jeremy A. Collins et al.

SRL-MPC integrates high-order control barrier functions with reinforcement learning for shape-aware multi-robot navigation, achieving 100% success in dense, complex scenarios.

Ruihua Han, Rui Gao, Zhe Liu et al.

Proposes Graph Engineering to organize tasks, coordinate heterogeneous agents, and manage states for system-level intelligence.

Yuyuan Feng, Zhishang Xiang, Chaobin Yang et al.

COTA enhances runtime intervention in LLM agents by comparing alternatives, improving performance in environments like WebShop.

Yanze Jiang, Mingxuan Li, Yuhao Wang et al.