This paper introduces TxFM, a masked autoencoder trained on 1.4 million RNA-seq samples, outperforming large-scale foundation models in gene representation learning.

Kian Kenyon-Dean, Alina Selega, Ihab Bendidi et al.

Proposes Functional Attention, transforming pointwise attention into linear operators in function spaces, achieving resolution-invariant PDE solving and 3D segmentation with superior performance.

Jiefang Xiao, Maolin Gao, Simon Weber et al.

This paper establishes the theoretical foundation for linear recurrent memory units (ALF) in partially observable reinforcement learning, constructing two linear filters that precisely replicate belief dynamics.

Yike Zhao, Onno Eberhard, Malek Khammassi et al.

HullFT employs convex reconstruction and gradient caching for efficient test-time fine-tuning, improving speed and quality tradeoff in large language models.

Alaa Khamis, Alaa Maalouf

Combining multi-objective genetic programming with survival tree optimization, this study enhances predictive accuracy and interpretability in survival analysis, validated on two real-world datasets.

Thalea Schlender, Peter A. N. Bosman, Tanja Alderliesten

SCOPE integrates a frozen LLM with an open-set plugin classifier, achieving 91.05% open-set detection accuracy and 96.63% anomaly correction in ATC readback monitoring.

Qihan Deng, Minghua Zhang, Yang Yang et al.

LearnWeak framework uses a stronger reference agent to identify model weaknesses, synthesizes targeted tasks, and improves small CUAs by 11.6% on average across 8 domains.

Suji Kim, Kangsan Kim, Sung Ju Hwang

BIRDNet encodes mined Boolean implication graphs into sparse, interpretable deep neural networks, achieving near state-of-the-art AUROC with 96x fewer active parameters on six biomedical datasets.

Tirtharaj Dash

SAERL leverages Sparse Autoencoder activations to model diversity, difficulty, and quality for LLM post-training data engineering, boosting Qwen2.5-Math-1.5B accuracy by 3%.

Yi Jing, Zao Dai, Jinwu Hu et al.

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

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

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.

Vector Policy Optimization (VPO) trains diverse policies to improve test-time search, achieving over 20% gains on best@k metrics across multiple tasks.

Ryan Bahlous-Boldi, Isha Puri, Idan Shenfeld et al.

Introduces curiosity-driven 3D exploration using persistent 3D Gaussian Splatting world model and Transformer policy, achieving 74.94% 3D coverage on HM3D.

Lily Goli, Justin Kerr, Daniele Reda et al.

The Matching Principle unifies nuisance-robust learning by estimating deployment nuisance covariance and regularizing encoder Jacobian accordingly; validated on 7B-parameter Qwen2.5-7B.

Vishal Rajput

Pion optimizer preserves spectrum via orthogonal equivalence transformation, enhancing LLM training stability.

Kexuan Shi, Hanxuan Li, Zeju Qiu et al.

Proposes a sparse-to-dense reward principle combining GRPO and OPD to enhance language model post-training.

Yuanda Xu, Hejian Sang, Zhengze Zhou et al.

MEME evaluates multi-entity and evolving memory tasks, exposing dependency reasoning failures in current systems.

Seokwon Jung, Alexander Rubinstein, Arnas Uselis et al.

The paper introduces a parameter-free online K-Means router leveraging geometric coupling for effective expert assignment, reducing load imbalance with only a slight perplexity increase.

Sagi Ahrac, Noya Hochwald, Mor Geva

KV-Fold: A training-free protocol for long-context inference achieving 100% exact-match retrieval.

Alireza Nadali, Patrick Cooper, Ashutosh Trivedi et al.