Proposed GADD algorithm achieves O(polylog(ε⁻¹)) sampling complexity for uniform-rate discrete diffusion models, significantly accelerating sampling.

Yuchen Liang, Ness Shroff, Yingbin Liang

MATCHA employs contrastive learning to improve semantic matching, achieving over 18% better accuracy than ROUGE-L.

Siran Li, Ece Sena Etoglu, Carsten Eickhoff et al.

Representation-conditioned diffusion models using DINO embeddings achieve high-quality, controllable image generation on LSUN and CelebA datasets.

Nithesh Chandher Karthikeyan, Jonas Unger, Gabriel Eilertsen

FinHarness reduces ASR to 15% on FinVault with 4.7× fewer advanced judge calls via inline lifecycle safety harness

Haoxuan Jia, Yang Liu, Bin Chong et al.

Proposed Normal Guidance regularization improves attention-based MIL slice-level localization on 4M+ CT slices, outperforming baselines.

Ethan Harvey, Dennis Johan Loevlie, Michael C. Hughes

Introduces ENPMR-Bench, a benchmark for proactive memory retrieval based on Maslow’s hierarchy, revealing significant deficiencies with current models, and outlining future directions.

Xing Fu, Yulin Hu, Mengtong Ji et al.

ReMoE boosts expert reuse by 26% through router fine-tuning in memory-constrained MoE inference.

Xiongwei Zhu, Xiaojian Liao, Tianyang Jiang et al.

BhashaSetu improves low-resource translation quality via corpus deduplication, reducing performance by 1.17 BLEU and 2.21 chrF++.

Param Thakkar, Anushka Yadav, Michael Tiemann et al.

Introduced a causal representation learning method to enhance recommendation systems' distribution generalization, achieving significant user engagement improvement on Spotify.

Yorgos Felekis, Michael O'Riordan, Oriol Corcoll et al.

Symmetric Attention Decomposition uses Hopfield stability and skew circulation to control SDXL’s fidelity–diversity trade-off.

Hyunmin Cho, Woo Kyoung Han, Kyong Hwan Jin

Introduces teachability metric for token selection in on-policy distillation, improving performance with only 5% tokens.

Yuanyi Wang, Su Lu, Yanggan Gu et al.

Proposes a behavioral cloning framework for scientific annotation, revealing hierarchical skill emergence, model scaling benefits, and transferability.

Ishaan Singh Chandok, Core Francisco Park

LLM-guided evolutionary co-evolution of constitutions achieves ~0.78 stable equilibrium in Public Goods Game arms race.

Ujwal Kumar, Arth Singh, Hershraj Niranjani et al.

SurfaceLoRA method reduces sensitive information inference risk in LLM-exported vectors while maintaining summarization performance.

Weixin Liu, Bowen Qu, Juming Xiong et al.

HydraPrompt employs adaptive asymmetric prompts and contrastive learning to detect synthetic images with 98.8% accuracy, outperforming SOTA.

Senyuan Shi, Hao Tan, Zichang Tan et al.

Study reveals algorithmic fragility and persona bias in LLM-generated autistic communication using a multi-agent qualitative analysis framework.

Naba Rizvi, Mohammed Rizvi, Harper Strickland et al.

Anchor formalizes enterprise workflows via constraint programming, mitigating artifact drift and enabling controlled task generation with certified solutions.

Maksim Ivanov, Abhijay Rana

AgingBench evaluates long-lived AI agents via four mechanisms, enabling diagnosis and targeted repair to sustain reliability.

Jianing Zhu, Yeonju Ro, John Robertson et al.

Unified Neural Scaling Law (UNSL) models multi-dimensional scaling of deep networks, improving performance extrapolation accuracy by over 10%.

Ethan Caballero, Priyank Jaini, David Krueger et al.

LoopMDM employs selective layer looping, reducing training FLOPs by 3.3× while matching or surpassing baseline performance, with flexible inference scaling.

Sanghyun Lee, Chunsan Hong, Seungryong Kim et al.