Proposes O²-CritiCuRL, combining offline analysis and online RL to identify critical reasoning steps, boosting multimodal reasoning accuracy and efficiency.

Wendi Deng, Hang Du, Guoshun Nan et al.

Proposed AAMSF framework for extreme volatility warning via multi-source anomaly fusion; achieved test AUC of 0.680.

Jin Qian, Zhangzhi Xiong, Mingrui Li et al.

GEMCo uses human-crafted proxy conversations validated against real data, enabling ethical sharing of sensitive counseling dialogues with minimal distribution gap.

Philipp Steigerwald, Eric Rudolph, Mara Stieler et al.

T3EM achieves top retrieval performance (nDCG@10=0.638) but incurs 7-14x latency of open-source models.

Madhav S Baidya

This study evaluates eight large language models (LLMs) in zero-shot generation of parent selection operators for symbolic regression in genetic programming, demonstrating competitive performance.

Hengzhe Zhang, Qi Chen, Bing Xue et al.

PlanCraft integrates progressive sketches and spatial constraints, reducing FID by 61.1% in residential scene generation.

Pengyu Zeng, Yuqin Dai, Jun Yin et al.

Proposed MCOF framework addresses sampling and constraint challenges in VAE-based data-driven problems.

Ye Shi

Study enhances legal QA performance via context-injected fine-tuning, showing significant gains for Qwen3.5 at 0.8B parameters.

Moniruzzaman Mahadi, Abrar Mohammed Tanzim Alam, Sayma Siddika Monalisa et al.

Study finds Chinese debates show higher semantic repetition than English, introducing 'Prior-Argument Similarity' metric.

Huiqian Lai

UltraViT optimizes vision encoders for on-device large models, achieving 1.7x speed improvement.

Ioannis Maniadis Metaxas, Adrian Bulat, Alberto Baldrati et al.

IKS-Instruct creates a 24,795-pair multilingual dataset covering 41 Indian Knowledge System techniques, significantly enhancing model cultural depth and pedagogical ability.

Shwetha Singaravelu, Gayathri Muruganantham, Lakshmi Rajendran et al.

Proposes BHARATI, a morphology-aware tokenizer with subword fertility analysis, reducing sequence length by 90% on classical Indian language corpora.

Poornima Kumaresan, Pavithra Muruganantham, Lakshmi Rajendran et al.

TOPOFE, a graph-structured multi-island evolutionary framework, significantly improves AutoFE performance on 29 datasets, surpassing state-of-the-art methods.

Sha Li, Naren Ramakrishnan

Proposes Co-E system with bidirectional graph-text memory for training-free multi-hop QA, outperforming baselines.

Hieu Man, Thien Huu Nguyen

Introduces X-Stage, a software-visible post-issue pipeline stage, using Burst-Gap model to optimize communication–computation overlap in DiT inference, boosting GPU throughput.

Jianwen Xian, Zhiyuan Xu, Yuchen Li et al.

Proposes NOPD, a self-distillation method that improves vision-language models without external supervision by leveraging prediction discrepancies between clean and corrupted inputs.

Shuai Wang, Daoan Zhang, Zhe Tang et al.

Introduced SQBench, a benchmark evaluating language models' task delivery in production workflows, with 220 tasks, combining functional completion and risk assessment, achieving a max of 60.5%.

Summer Sun

Proposes a data scaling law for high-precision robotic manipulation, described by log(N) ∝ 1/(P-c).

Cuijie Xu, Yuanfan Xu, Min Xue et al.

SearchArt employs verification-driven synthetic data generation and multi-stage fine-tuning, achieving 74.39 on BrowseComp-ZH with only 27B parameters.

Lang Mei, Xiaohan Yu, Chong Chen et al.

SAGE governs AI across its lifecycle; 840 endpoint calls showed low observed harmful compliance under a narrow single-turn protocol.

Mahdi Eslamimehr