TRUSTMEM enhances LLM agents' memory consolidation trustworthiness, improving HaluMem extraction by 12.14 F1 points.

Tianyu Yang, Sudipta Paul, Vijay Srinivasan et al.

This study systematically evaluates automatic quality metrics versus human perception and downstream land-cover segmentation performance for Earth observation synthetic data.

Ümit Mert Çağlar, Alptekin Temizel

TAIS method verifies speculative decoding safety at zero temperature with 48,072 samples showing no safety divergence.

Sahil Kadadekar

Edge-cloud speculative decoding enhances multi-tenant capacity at low RTT, limited single-request latency benefits.

Yuan Lyu, Bharath Irukulapati, Jaya Prakash Champati

Using reasoning tokens as a proxy for reaction time, the study analyzes vision-language models' search behaviors across classic paradigms, revealing partial human-like signatures.

Farahnaz Wick

Proposes a universal quantum Schur transform for efficient, lossless conversion between first- and second-quantized many-body states across particle statistics.

Jack S. Baker, Gaurav Saxena, Thi Ha Kyaw

FLUX3D employs Diffusion-Aligned Structured Latents and sparse-structure-aware diffusion transformer to generate high-fidelity 3D Gaussian point clouds, outperforming SOTA methods.

Haorui Ji, Weizhe Liu, Hongdong Li et al.

Proposes a multidimensional evaluation framework combining technical metrics and user-centered methods for six AAC problem spaces, enhancing AI system fairness and adaptability.

Blade Frisch, Will Wade, Dylan Gaines et al.

Introduces a structural certification framework using deep goal composition to filter specific transitions, with an error bound of O(1/n)+δ, enabling local validation of internal world models.

Yikai Lu, Yifei Wu, Xinyu Lu et al.

This paper critically analyzes Andreas & Günther's seven definitions of actual causation, revealing their logical equivalence and exposing flaws in their categorical distinctions.

Sander Beckers

Grad Detect leverages layer-wise gradients for single-pass hallucination detection, outperforming confidence baselines with 94-99% accuracy.

Anand Kamat, Daniel Blake, Brent M. Werness

Proposes a four-module analytical framework to evaluate 12 agent memory systems across diverse workloads, revealing workload-architecture matching importance.

Wei Zhou, Xuanhe Zhou, Shaokun Han et al.

Introducing inertia into Dirac-Frenkel dynamics enhances robustness for nonlinearly parametrized solutions, providing well-posedness and error bounds, especially in ill-conditioned scenarios.

Matteo Raviola, Benjamin Peherstorfer

Using a fitted no-repetition scaling law, quantifies systematic damage caused by repeated data, revealing an intermediate repeat count causes maximum loss, with damage scaling as a power law with model size.

Jessica Chudnovsky, Joshua Kazdan, Noam Levi et al.

SER method enhances video reasoning with Semantic Evidence Rewards, achieving a 3.0-point mLGM improvement on V-STAR.

Sheng Xia, Zhengqin Lai, Tianxiang Jiang et al.

ReTVL leverages sparse retry event supervision to capture local mistake-recovery dynamics, outperforming progress-based models in fine-grained value estimation.

Xinyao Qin, Junjie Lu, Kaixin Wang et al.

Developed sample complexity bounds for unbalanced entropic OT, demonstrating geometric stability and high-probability guarantees.

Francisco Andrade, Gabriel Peyré, Clarice Poon

MemClaw addresses four failure modes in multi-agent LLM systems through governed shared memory, ensuring efficient knowledge management.

Yanki Margalit, Nurit Cohen-Inger, Erni Avram et al.

NatureBench evaluates AI coding agents on 90 scientific tasks; strongest model surpasses SOTA in only 17.8%.

Yuru Wang, Lejun Cheng, Yuxin Zuo et al.

PETRA leverages energy-domain classification and synthetic supervision to improve petroleum engineering retrieval, boosting first-stage nDCG from 0.703 to 0.763.

Kirill Dubovikov, Omar El Mansouri, Hachem Madmoun et al.