bioMoR enhances genomic learning efficiency via biology-guided recursion mixture, boosting macro-F1 by 8.2%.

Koushik Howlader, Tirtho Roy, Md Tauhidul Islam et al.

Introduces the 'Horizon Gap,' analyzing LLMs' planning, memory, and execution challenges in long-horizon tasks via 1,547-paper survey.

Mingguang Chen, Licheng Wang, Bo Qu

Proposes SYF, an LLM-based interactive recommendation system enabling multimodal real-time content control.

Ziyun Xu, Bosen Ding, Yue Zhang et al.

Proposed an Active Interaction-Aware Path Integral method using Ego-Conditioned Generative Predictions to enhance safety and efficiency in dense traffic scenarios.

Khaled A. Mustafa, Mohamed-Khalil Bouzidi, Christian Schlauch et al.

Introduces block-hybrid attention to retrofit LLaDA 2.1-mini, achieving 1.7× inference speedup with minimal performance loss.

Jinha Kim, Younghun Roh, Jaeyeon Kim

This study compares programmatic tool calling (PTC) with native JSON calls across 14 models on BFCL v4, showing a 10.6% accuracy boost for PTC, demonstrating robustness and scalability.

Ishan Patel, Sahil Sen, Elias Lumer et al.

This paper analyzes challenges in evaluating explanation methods for static and evolving data, proposing bias detection and concept drift explanations with experimental validation.

Jerzy Stefanowski

Tytan combines symbolic analysis and LLM inference to automatically construct semantic schemas from relational databases, enhancing data understanding and querying.

Donna Hooshmand, Shubham Shahi, Cameron Barrie et al.

Proposes a reference-free, multi-metric framework using LLM judges to evaluate conversational benchmarks' consistency, complexity, and coverage, validated via synthetic and manual benchmarks.

Noam Koren, Roy Bar-Haim, Abigail Goldsteen

Introduces GB/T-Bench and GB/T-Reviewer, leveraging hierarchical error taxonomy and multi-agent collaboration to significantly improve rule-based national standard document review.

Tao Wang, Qihao Yang, Rongjiao Liang et al.

Proposes Ranking-based Reward Construction (RRC) to leverage generative reward models via relative rankings, improving RL performance with significant gains on benchmarks.

Chenglong Wang, Ziming Zhu, Yifu Huo et al.

HarnessOpt-Bench benchmark evaluates 5 frontier LLMs in costly, stochastic harness optimization, revealing significant model differences and room for improvement.

Varun Ursekar, Apaar Shanker, Yash Maurya et al.

CAV and TopK SAE auditing show that concept recoverability is not equivalent to influence on speaking scores.

Arya Labroo, Mengjie Qian, Kate Knill

Proposes SG-TULA, a subgradient-based Langevin sampling method with explicit convergence bounds for non-convex, non-smooth, superlinear potentials.

Iosif Lytras, Nikolaos Makras, Sotirios Sabanis

Proposes ErgoSurf combining online GPIS surface reconstruction with ergodic control for unknown surfaces, achieving near-ground-truth accuracy.

Stefan Schneyer, Timo Bachmann, Maged Iskandar et al.

Prior-SG formulates scene graph generation as a probabilistic alignment problem, integrating multi-scale feature fusion and graph optimization to achieve robust semantic region segmentation in complex environments.

Giorgio Tonetti, Laurent Kneip, Abel Gawel et al.

Proposes a verifiable regularity criterion based on the Sobolev regularity of the Radon–Nikodym density, ensuring boundedness and Hilbert–Schmidt properties of conditional expectation operators (CEOs) and embeddings, with applications in nonparametric regression, Bayesian inverse problems, and Koopman operators.

Maximiliano Hertel, Ilja Klebanov, Manuel Schaller et al.

Proposes a query-optimal algorithm for simulating time-dependent Hamiltonians with error ε using O(αT+log(1/ε)/log(e+log(1/ε)/(αT))) queries.

Boyang Chen, Minbo Gao, Xinzhao Wang et al.

Gated Hindsight Distillation (GHD) leverages next screenshots as privileged training info, significantly improving mobile GUI agent success rates.

Weiwei Li, Junzhuo Liu, Tong Chu et al.

Proposes TensorCast, a decoupled distributed tensor management layer, enhancing reuse and scalability in LLM infrastructure.

Yuhan Zhou, Yuchu Luo, Hao Nie et al.