Proposes AgenticRS, a self-evolving recommendation framework using reinforcement learning and LLMs for autonomous module optimization.

Jinxin Hu, Hao Deng, Lingyu Mu et al.

AutoModel employs three core agents—AutoTrain, AutoFeature, AutoPerf—for full lifecycle automation, reducing manual effort and improving recommendation performance.

Hao Zhang, Jinxin Hu, Hao Deng et al.

Proposed ARTA enhances multivariate time-series anomaly detection robustness via sparsity-constrained adversarial perturbations, outperforming SOTA benchmarks.

Hadi Hojjati, Narges Armanfard

DiReCT improves VideoPhy physical commonsense score by 16.7% without increasing training time.

Abolfazl Meyarian, Amin Karimi Monsefi, Rajiv Ramnath et al.

ENAP learns symbolic structures from visuomotor trajectories, outperforming SOTA methods by 27% in low-data regimes.

Yiyuan Pan, Xusheng Luo, Hanjiang Hu et al.

Proposes dynamic retargeting and control-guided RL for humanoid running at 3.3m/s, enabling autonomous, controllable, high-speed locomotion.

Zachary Olkin, William D. Compton, Ryan M. Bena et al.

Fus3D leverages pretrained multi-view geometry transformer latents to directly regress dense SDF in under 3 seconds, enabling fast, pose-free 3D reconstruction.

Laura Fink, Linus Franke, George Kopanas et al.

Proposes Kitchen Loop framework enabling autonomous software evolution via specification-driven testing, with 285+ iterations and zero regressions.

Yannick Roy

WebTestBench evaluates end-to-end web testing with models scoring below 30% F1, highlighting significant performance gaps.

Fanheng Kong, Jingyuan Zhang, Yang Yue et al.

ETA-VLA reduces computation by 32% via temporal fusion and sparsification, retaining 94% accuracy.

Yiru Wang, Anqing Jiang, Shuo Wang et al.

GDPO-Listener generates expressive head motions via Auto-Regressive Flow Matching and Group reward-Decoupled Policy Optimization.

Zhangyu Jin, Maksim Siniukov, Deuksin Kwon et al.

Exons-Detect uses hidden-state discrepancies to identify exonic tokens, boosting AI text detection robustness without training.

Xiaowei Zhu, Yubing Ren, Fang Fang et al.

Systematic characterization of off-wafer pulse communication in BrainScaleS, analyzing throughput, delay, jitter, and pulse loss with experimental validation.

Bernhard Vogginger, Vasilis Thanasoulis, Johannes Partzsch et al.

Multi-Answer RL trains models to generate multiple plausible answers in one pass, improving diversity and calibration, with 50% accuracy boost on coding tasks.

Isha Puri, Mehul Damani, Idan Shenfeld et al.

PyHealth framework evaluates attention mechanisms in clinical time-series models; Chefer method proves most effective and efficient.

Yongda Fan, John Wu, Andrea Fitzpatrick et al.

GoldiCLIP balances supervision signals for data-efficient vision-language pretraining on just 30 million images.

Deen Dayal Mohan, Hossein Souri, Vitali Petsiuk et al.

AVControl leverages LTX-2 with LoRA adapters for efficient multi-modal audio-visual control, achieving high performance with minimal training steps.

Matan Ben-Yosef, Tavi Halperin, Naomi Ken Korem et al.

SlopCodeBench evaluates how coding agents' code quality degrades over long iterative tasks, revealing increasing code bloating and complexity, with a maximum solve rate of 14.8%.

Gabriel Orlanski, Devjeet Roy, Alexander Yun et al.

Proposed a Markovian framework for auditing agentic AI reliability and oversight cost, improving state-action blind mass by 12.53%.

Biplab Pal, Santanu Bhattacharya

Latent-WAM achieves efficient end-to-end autonomous driving with spatially-aware and dynamics-informed latent world representations, scoring 89.3 on NAVSIM v2.

Linbo Wang, Yupeng Zheng, Qiang Chen et al.