Introduces RP-Regret for adaptive opponents, with algorithms achieving sublinear regret and better equilibria in repeated games.

Mingyang Liu, Asuman Ozdaglar, Tiancheng Yu et al.

Proposes Polynomial Weight Preconditioning (PC) layer to regulate singular-value spectrum, accelerating LLM pretraining; achieves 2× speedup on Llama-1B with no inference overhead.

Senmiao Wang, Tiantian Fang, Haoran Zhang et al.

GraphDETR formulates subgraph detection as set prediction, achieving 91.2 AP on molecular datasets with graphs up to 1000 nodes and 50-node substructures.

Dexiong Chen, Till Hendrik Schulz, Karsten Borgwardt

Proposes an algebraic identity and low-rank SVD approximation to compute mean curvature efficiently on high-dimensional data manifolds, reducing complexity from O(m^4) to near O(k^2 m).

Alexandre L. M. Levada

MolE-RAG integrates literature, molecular features, and structural similarity to enhance LLM-based molecular property prediction, boosting ROC-AUC by up to 28% and reducing RMSE by 67%.

Joey Chan, Wonbin Kweon, Ashley Shin et al.

Proposes DistIL, a distributional imitation learning algorithm with monotonic improvement guarantees, leveraging rich feedback for complex reasoning tasks.

Rishabh Agrawal, Jacob Fein-Ashley, Paria Rashidinejad

Skill-RM unifies heterogeneous evaluation criteria via agent skills, enabling dynamic resource orchestration, outperforming traditional judges with a 3-6% improvement on RewardBench2.

Tao Chen, Gangwei Jiang, Pengyu Cheng et al.

Introducing the 'Sleep' paradigm with Knowledge Seeding and Dreaming mechanisms enables LLMs to self-modify and consolidate memories for continual learning.

Ali Behrouz, Farnoosh Hashemi, Vahab Mirrokni

Proposes ROSA, a reward distribution-based framework for inducing diverse behaviors without performance loss, leveraging set functions and unbiased gradient estimators.

Anthony GX-Chen, Ankit Anand, Gheorghe Comanici et al.

This paper introduces an equilibrium propagation (EP)-based training method for deep predictive coding networks (PCNs), achieving 13.23% Top-5 error on ImageNet with a 10-layer VGG model, close to the 12.2% baseline of backpropagation.

Tugdual Kerjan, Rasmus Høier, Benjamin Scellier

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