OGAS method improves worst-case reliability of PDE surrogates via generative active sampling.

Pierre Cesar, Sofya Dymchenko, Abhishek Purandare et al.

RLDT, a density transport-based reinforcement learning algorithm, significantly improves reward quality and convergence speed in continuous control tasks.

Boshu Lei, Kostas Daniilidis, Antonio Loquercio

EinSort leverages index sorting to reveal low-rank structures in LLM weights, achieving superior compression with minimal performance loss.

Toshiaki Koike-Akino, Jing Liu, Ye Wang

STAR-KV employs soft-thresholding for adaptive low-rank KV cache compression, achieving up to 75% compression, 6.9× speedup, and 20× overall reduction.

Priyansh Bhatnagar, Ashkan Moradifirouzabadi, Se-Hyun Yang et al.

LH-NeF adds hierarchical locality to neural-field tokens, cutting memory 42× and enabling 133× larger batches.

Alonso Urbano, David W. Romero, Max Zimmer et al.

PACI introduces asynchronous pipeline training with gradient accumulation to bound weight drift, boosting efficiency by up to 1.69×.

Itay Elam, Eliron Rahimi, Avi Mendelson et al.

Proposes CoMetaPNS, integrating continual Bayesian GMM with set-conditioned generative models for personalized cardiac electrophysiology simulation, achieving superior accuracy and anti-forgetting.

Ryan Missel, Xiajun Jiang, Linwei Wang

SlimSearcher enhances training efficiency via adaptive reward gating, reducing tool calls by 17%-58%.

Zequn Xie, Junjie Wang, Dan Yang et al.

Introduces ShallowBench, a benchmark for evaluating generative drug models on low-concavity targets using Alpha Shape volume differences.

Saket Reddy, Shiwei Liu

PoLar algorithm dynamically skips or repeats layers to enhance LLM inference efficiency and accuracy.

Ziyue Li, Yang Li, Tianyi Zhou

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

Proposes Compress-Distill, compresses reasoning traces to 8.6-21%, reduces training tokens by 12-30%, speeds up training 2-7.6×, retains 96% accuracy.

Maxime Griot, Paul Steven Scotti, Tanishq Mathew Abraham

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.

SelfBootTok decomposes images into global and local tokens via self-supervised learning, achieving 1.56 gFID with only 64 tokens, surpassing previous methods.

Haozhe Chi, Jinghan Li, Hao Jiang et al.

Zeroth-order optimization reveals a single dominant decoding layer for efficient LLM fine-tuning, achieving up to 4.52× speedup.

Wanhao Yu, Ziyan Wang, Zheng Wang et al.

Proposes Representation Curriculum to enhance ranking robustness through staged training, showing significant improvement in cold-start scenarios.

Ehsan Ebrahimzadeh, Sina Baharlouei, Abraham Bagherjeiran

Agentic Monte Carlo (AMC) uses Bayesian posterior sampling with SMC to optimize black-box LLM agents, outperforming prompting and GRPO.

Dae Yon Hwang, Raunaq Suri, Valentin Villecroze et al.