The paper argues LLMs should learn personalized rather than aggregated preferences, citing social choice theory and experimental data.

Cristina Garbacea

GNMR controls stability in low-precision language model training by comparing gradient norms with historical means.

Boao Kong, Weichen Jia, Engao Zhang et al.

Proposes semantic space matching using SSL features with Sinkhorn divergence, reducing ImageNet FID by 39×, improving one-step generative quality.

Hugues Van Assel, Edward De Brouwer, Saeed Saremi et al.

Proposes a kernel spectral method for semi-supervised regression with noisy proxy variables, achieving near-oracle rates under controlled noise conditions.

Kwangho Kim, Jisu Kim

EST-PRM framework stress-tests dense process reward models using three label-preserving transformations, revealing significant vulnerabilities across models.

Ibne Farabi Shihab, Fariya Afrin, Sanjeda Akter et al.

Proposed Grounded Decoding framework improves factual consistency in RAG without training.

Ibne Farabi Shihab, Fariya Afrin, Sanjeda Akter et al.

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.

Proposed a constrained max-min MORL framework using convex optimization, validated convergence and practical effectiveness across multiple domains.

Giseung Park, Hyunyoung Nam, Woohyeon Byeon 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.

Introducing Fixed-Point Masked Generative Models (FP-MGMs), which use shared attention layers with a fixed-point solver for adaptive depth, reducing parameters by 38.8% and training time by 11.5%.

Andrea Miele, Yiming Qin, Alba Carballo-Castro et al.

Annealed Softmax Greedy achieves near-optimal Bayes regret in many-armed Bayesian bandits.

William Overman, Mohsen Bayati

FLAG optimizes flow policy with latent-augmented guidance, excelling in high-dimensional control tasks.

Sungha Kim, Gawon Lee, Jusuk Lee et al.

This study analyzes effectiveness and RL training efficiency, revealing high sensitivity in evaluation and proposing two acceleration techniques.

Tong Liu, Cheng Qian, Matej Cief et al.

Enhancing selective classification accuracy and cost-efficiency using PairSel algorithms.

Harsh Vardhan, Sunav Choudhary, Natwar Modani et al.

Proposes CFO algorithm using sequential fine-tuning with augmented Lagrangian to balance reward maximization and constraints in molecular design.

Sven Gutjahr, Riccardo De Santi, Luca Schaufelberger et al.

The study shows padded Transformers are robust in expressivity, influenced by numerical precision and model depth.

Anej Svete, William Merrill, Ryan Cotterell et al.

DisjunctiveNet employs hierarchical convex hull relaxations to enforce hard, input-dependent mixed-integer linear constraints end-to-end, achieving 100% rule satisfaction.

Shraman Pal, Can Li

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