Proposes Representation Curriculum to enhance ranking robustness through staged training, showing significant improvement in cold-start scenarios.

Ehsan Ebrahimzadeh, Sina Baharlouei, Abraham Bagherjeiran

Introduced PERSUASIONTRACE, leveraging Bayesian networks to model multi-turn belief updates, scoring near humans (81 vs 80).

Jared Moore, Noah Goodman, Nick Haber et al.

Agentic Monte Carlo (AMC) uses Bayesian posterior sampling with SMC to optimize black-box LLM agents, outperforming prompting and GRPO.

Dae Yon Hwang, Raunaq Suri, Valentin Villecroze et al.

Proposes DistIL, a distributional imitation learning algorithm with monotonic improvement guarantees, leveraging rich feedback for complex reasoning tasks.

Rishabh Agrawal, Jacob Fein-Ashley, Paria Rashidinejad

HORIZON uses recoverability-governed curriculum to expand physical domains, enhancing quadruped robots' zero-shot transfer abilities.

Chenhao Bai, Liqin Lu, Kaijun Wang et al.

ZipSplat uses scene tokens to decouple Gaussian placement from pixels, achieving high-quality scene reconstruction with 6× fewer Gaussians, and adjustable quality-efficiency trade-off.

Alexander Veicht, Sunghwan Hong, Dániel Baráth et al.

Depth-Attention enhances language models by cross-layer value mixing, improving accuracy by up to 2.3 points.

Boyi Zeng, Yiqin Hao, Zitong Wang et al.

Flash-WAM uses modality-aware step distillation to reduce inference from 50 steps to 1, achieving 23× speedup while maintaining high task success rates.

Arman Akbari, Ci Zhang, Arash Akbari et al.

M³Eval, grounded in cognitive psychology, assesses multi-modal video memory across four dimensions with controlled tasks and quantitative metrics.

Jie Huang, Ruixun Liu, Sirui Sun et al.

Proposes Dual-Stream MLP with knowledge distillation, achieving state-of-the-art CTR prediction performance with simplified architecture.

Kesha Ou, Zhen Tian, Wayne Xin Zhao et al.

Proposes trajectory-based safety alignment, significantly improving LLM robustness against mid-inference token injections.

Kyungmin Park, Taesup Kim

Curvature-aware dynamic precision control using L-BFGS curvature info balances PINN accuracy and efficiency.

Yingjie Shao, Ioannis N. Athanasiadis, George van Voorn et al.

LifeSide uses multi-session Memory-Emotion-Environment loops to evaluate lifelong digital companions' long-term memory, understanding, privacy, and emotional support, based on 2000 personas and 111K tasks.

Yuqian Wu, Zhijie Deng, Wei Chen et al.

BiNSGPS uses bidirectional neuro-symbolic feedback, achieving 90.5% on Geometry3K and 90.1% on PGPS9K.

Qi Wang, Peijie Wang, Fei Yin et al.

RAMPART optimizes LLM agent memory with priority-aware runtime transformation, enhancing task success.

Nikodem Tomczak

Constructed individual digital twins from SOEP microdata; optimal info depth at 75% entropy yields 78.8% accuracy, model choice and embedding matter.

Leonard Kinzinger, Jochen Hartmann

VCIFBench evaluates complex video instruction following, covering 306 tasks with multi-constraint challenges, revealing significant gaps in current models.

Huangchen Xu, Yuan Wu, Yi Chang

HMARS enhances long-context reasoning by using a hierarchical multi-agent memory system, significantly improving evidence coverage.

Zeju Li, Ziyang Zheng, Yizhou Zhou et al.

Proposed a difficulty-aware SFT-then-RL framework to enhance small language model reasoning.

Chongyang He, Rui Zhang, Zixuan Wang et al.

LoopMoE combines sparse routing with iterative computation, improving performance across 9 benchmarks.

Wenkai Chen, Tianshu Li, Wenyong Huang et al.