MMAO: bio-inspired self-adaptive optimizer using endogenous resource loops for continuous and discrete problems.

Jinliang Xu, Liping Ma

CAPE uses GPT-4o to explain spatial document layouts with layout-grounded context across news and scholarly maps.

Wei Liu, John Wenskovitch, Chris North et al.

MultiHashFormer employs a multi-hash signature mechanism supporting causal language modeling, outperforming standard Transformers across 100M-3B parameters, with zero-parameter multilingual vocabulary expansion.

Huiyin Xue, Atsuki Yamaguchi, Nikolaos Aletras

Introduced Parallel Rollout Approximation (PRA) achieving 1.94 FID on ImageNet-1K.

Jiayi Xu, Di He, Guolin Ke

VASAE introduces vocabulary-aligned anchoring to train SAE features with intrinsic token names, maintaining reconstruction quality and achieving over 90% feature-token alignment.

Kairui Zhang, Ziwen Yu, Zahraa S. Abdallah et al.

Proposes SD-GPS framework using QwenVL3-2B for autoformalization and lemma proposing, achieving 86.4% accuracy on Geometry3K.

Can Li, Ting Zhang, Junbo Zhao et al.

LocalNav distills frontier VLMs and RL to enable ObjectNav on embedded devices, reducing inference latency by 82.8%.

Nicolas Baumann, Liam Boyle, Pu Deng et al.

Proposed CSD, a content-aware speculative decoding algorithm, achieving 4.33× speedup on MS-COCO.

Mingcheng Wang, Junbo Qiao, Yunchen Li et al.

Video-MME-Logical benchmark reveals significant gaps in MLLMs' video temporal-logical reasoning.

Hohin Kwan, Hongyu Li, Ray Zhang et al.

ATOD combines annealed schedule and turn-level uncertainty weighting to boost multi-turn agent performance.

Qitai Tan, Zefang Zong, Mo Li et al.

NormGuard applies reward-preserving norm constraints to suppress velocity norm inflation in RL fine-tuning, improving image quality.

Tianlin Pan, Lianyu Pang, Cheng Da et al.

PerturbCellRL uses four biological verifiers to post-train scDFM, improving single-cell consistency after 1,600 RL steps while preserving population-level competitiveness.

Dongxia Wu, Mingyu Li, Yuhui Zhang et al.

Introduces Masked Language Flow Models combining masking and flow models to enhance multi-step reasoning.

Iskander Azangulov, Kianoosh Ashouritaklimi, Leo Zhang et al.

Introduces Ko-WideSearch, a Korean breadth-search benchmark with 228 tables, evaluating web agents' ability for exhaustive set enumeration and attribute filling.

Minbyul Jeong

RAC reduces policy bias by 47.9x via delay-aware reward correction for RLHF.

Arnav Raj

VulcanVoxel reconstructs blade insertion feasibility in 3D occupancy fields, achieving 0.89 coverage.

Tianyu Li, Harpreet Sawhney, Minju Jung et al.

Proves that shared embedding architectures cannot achieve perfect prompt injection prevention due to inseparability of instructions and data.

Dewank Pant, Shruti Lohani, Avijit Kumar

DMV-Bench tests multimodal agents' visual memory; DualMem excels in long-chain tasks.

Yujin Tang, Chenming Shang, Ruize Xu et al.

QueenBee Planner self-evolves communication topologies using evidence-driven rules, reducing RMSE from 12.53 to 7.87 and communication costs in multi-agent LLM systems.

Congjia Tian, Yuhang Yao, Jiaming Cui

PolyFlow uses continuous topology embedding flow matching for artist-style mesh generation, outperforming state-of-the-art methods.

Chunshi Wang, Haohan Weng, Junliang Ye et al.