Alignment-Aware Selection

Follow this topic Ask about this topic

Momentum

3 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 37

All topics

VASC: Value-Aware Sparse Attention with Cross-Layer Memory for Efficient 3D Reconstruction
Oct 1, 2026Junyi Wu, Fanqing Kong, Leyang Chen +23D Reconstruction Visual Geometry Grounded Transformer
Shanghai Jiao Tong University
What Should an Agent Remember? Disentangling Retention from Retrieval in Bounded-Memory Evaluation
Sep 30, 2026Juli HuangRetention Bounded-Memory
Stanford University
From Checkpoint Variation to Selection Gains in Supervised Fine-Tuning
Sep 29, 2026Yupeng Chang, Wenxuan Zhang, Yuan WuSupervised Finetuning Alignment-Aware Selection
School of Artificial Intelligence, Jilin University · Singapore University of Technology and Design · Key Laboratory of Symbolic Computation and Knowledge Engineering, Jilin University
EconSkills: Studying Skill Transfer and Retrieval for Web Agents on Live Economic Data
Sep 17, 2026Yinzhu Quan, Zefang LiuEconomies Web Agents
Georgia Institute of Technology Atlanta, GA, USA · Capital One San Jose, CA, USA
Latent Mechanisms of Language Control in Multilingual Language Models
Aug 31, 2026Ryo Mitsuhashi, Sabri Boughorbel, Majd HawaslyMultilingual Language Models Code-Switching
Princeton University New Jersey, USA · Prince Sattam bin Abdulaziz University Riyadh, Saudi Arabia · QCRI, Hamad Bin Khalifa University, Doha, Qatar
Exact Recovery Thresholds for Weighted Data Selection in Vector-Valued Linear Regression
Aug 31, 2026Guangjian ZhangAlignment-Aware Selection Spectral Norm
Epiplexity Guided Data Selection and Generation for Out-of-Distribution Generalization
Aug 12, 2026Ellen Su, Andres Potapczynski, Shikai Qiu +2Alignment-Aware Selection Out-Of-Distribution
New York University · Inherent
Agentic Instruction Data Selection: Let DataMaster Interpret Your Intent
Aug 11, 2026Fanqi Zhou, Qiaosheng Chen, Zixian Huang +1Alignment-Aware Selection Data Science Agents
State Key Laboratory of Novel Software Technology, Nanjing University · Shanghai Artificial Intelligence Laboratory
SFGA: A Statistics-First Gating Architecture with Adjudicative Escalation for Trustworthy SFT Data Procurement
Jul 21, 2026Arther Tian, Alex Ding, Simon Wu +1Gating Alignment-Aware Selection
DGrid AI
Online Data Selection Is Implicit Alignment
Jul 8, 2026Aoxiong Zeng, Yuxin Yang, Xiangquan YangAlignment-Aware Selection Model Fine-Tuning
East China Normal University · Shanghai University
Understanding Domain-Aware Distribution Alignment in Budgeted Entity Matching
Jun 25, 2026Nicholas Pulsone, Gregory Goren, Roee ShragaDistributional Alignment Entities
Worcester Polytechnic Institute · Worcester, MA · Israel
BLADE: Scalable Bi-level Adaptive Data Selection for LLM Training
Jun 17, 2026Jiaxing Wang, Deping Xiang, Jin Xu +9Alignment-Aware Selection Large Language Model Training
QueryMarket: Cost-Aware Online Active Learning in Data Markets
Jun 16, 2026Xiwen Huang, Pierre PinsonPool-Based Active Learning Active Learning
Dyson School of Design Engineering, Imperial College London, London, SW7 2DB, U.K. · Dyson School of Design Engineering, Imperial College London, London, U.K. · Halfspace (part of Accenture) +2
Spokes: Optimizing for Diverse Pretraining Data Selection
Jun 13, 2026Clarence Lee, Yejin Choi, Luke Zettlemoyer +2Alignment-Aware Selection Subsampling
DSO National Laboratories · Stanford University · University of Washington
Hubs or Fringes: Pretraining Data Selection via Web Graph Centrality
Jun 9, 2026Vedant Badoni, Danqi Chen, Xinyi WangMultiple Centrality Measures Alignment-Aware Selection
Princeton Language and Intelligence
Unifying Data, Memory, and Compute Efficiency in LLM training: A Survey
Jun 9, 2026Vanessa Schmidt, Huy Hoang Nguyen, Cédric Jung +2Alignment-Aware Selection Large Language Model Training
Chair of Information Theory and Data Analytics (INDA), RWTH Aachen University, 52074 Aachen, Germany · AIT Austrian Institute of Technology GmbH, 1210 Vienna, Austria · Automation and Control Institute, Technische Universität Wien (TUW), 1040 Vienna, Austria
Unlocking Latent Value: Taxonomy-Guided Recovery of High-Performing Data from Low-Tier Web Corpora
Jun 5, 2026Neeraj Varshney, Sanket Lokegaonkar, Nasser Zalmout +3Taxonomy Data-Curation
Amazon
HARP: Efficient Data Selection for Finetuning Large Language Models
Jun 5, 2026Ning Wang, Zhengxin Zhang, Maosen Tang +3Alignment-Aware Selection Downstream Reasoning
Cornell University · The Hong Kong University of Science and Technology
MLSkip: Data Skipping for ML Filters via Lightweight Metadata
Jun 2, 2026Mihail Stoian, Mark Gerarts, Pascal Ginter +3Data Lakes Skip
University of Technology Nuremberg Nuremberg, Germany · Hasselt University Hasselt, Belgium · Technical University of Munich Munich, Germany
Towards Efficient LLMs Annealing with Principled Sample Selection
May 29, 2026Yuanjian Xu, Jianing Hao, Wanbo Zhang +2Large Language Model Training Alignment-Aware Selection
The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China · Microsoft Research Asia, Beijing, China · Fudan University, Shanghai, China
MIRA: Mid-training Rubric Anchoring for Source-Aware Data Selection
May 28, 2026Haowen Wang, Yaxin Du, Jian Yang +9Alignment-Aware Selection Training Data
1Beihang University · 2IQuest Research · 3Shanghai Jiao Tong University +2
PRISM: Preference-Aware Influence Function Based Data Selection Method for Efficient Fine-Tuning
May 20, 2026Qihao Lin, Guanxu Chen, Dongrui Liu +1Alignment-Aware Selection Model Fine-Tuning
Shanghai Artificial Intelligence Laboratory
A Bitter Lesson for Data Filtering
May 19, 2026Christopher Mohri, John Duchi, Tatsunori HashimotoModel Size Pretraining
Department of Computer Science Stanford University · Departments of Statistics and Electrical Engineering Stanford University
SEED: Targeted Data Selection by Weighted Independent Set
May 15, 2026Yuan Zhang, Lifeng Guo, Junwen Pan +5Alignment-Aware Selection Adaptive Sampling
School of Computer Science, Peking University · Beijing University of Posts and Telecommunications · Tianjin University +2
Beyond What to Select: A Plug-and-play Oscillatory Data-Volume Scheduling for Efficient Model Training
May 14, 2026Suorong Yang, Hanqi Zhu, Hai Gan +4Alignment-Aware Selection Regularization
1National University of Singapore · 2Nanjing University · 3Hokkaido University +1
WASHH: An Anchor-Aware Whale-Guided Selection Hyper-Heuristic for Continuous Optimization and SVC Configuration
May 13, 2026Yifu Zhao, Xiaofan Zou, Junhao Wei +9Black-Box Optimization Metaheuristics
Faculty of Applied Sciences, Macao Polytechnic University, Macao, 999078, China · School of Mechanical and Electrical Engineering and Automation, Shanghai University, Shanghai, 200444, China · Pazhou Lab (Huangpu), Guangzhou, 510555, China +2
SLAP: Stratified Loss-based Pruning for On-Policy Data-Efficient Instruction Tuning
May 13, 2026Run Zou, Jianhang Ding, Yifan Ding +3Instruction Tuning Alignment-Aware Selection
Alibaba International Digital Commerce Group, HangZhou, China · Hangzhou Lingju Intelligence AI Lab, Hangzhou, China · Hangzhou Dianzi University, HangZhou, China
Data Difficulty and the Generalization--Extrapolation Tradeoff in LLM Fine-Tuning
May 13, 2026Siyuan Liu, Tinghong Chen, Xinghan Li +2Large Language Model Fine-Tuning Model Fine-Tuning
IIIS, Tsinghua University · College of AI, Tsinghua University · Shanghai Qi Zhi Institute +1
How Faithful Is Trajectory-Based Data Attribution? Error Sources, Remedies, and Practical Guidelines
May 12, 2026Junwei Deng, Pingbang Hu, Suliang Jin +4Alignment-Aware Selection Log-Ratio-Based Gaussian Trust Weight
University of Illinois Urbana-Champaign · University of Michigan · Princeton University +1
Constraint-Data-Value-Maximization: Utilizing Data Attribution for Effective Data Pruning in Low-Data Environments
May 11, 2026Danilo Brajovic, David A. Kreplin, Marco F. HuberAlignment-Aware Selection Limited Data
Fraunhofer IPA, Stuttgart, Germany · Institute of Industrial Manufacturing and Engineering IFF, University of Stuttgart, Germany · Hochschule Heilbronn, Germany
Is Data Shapley Not Better than Random in Data Selection? Ask NASH
May 11, 2026Xiao Tian, Jue Fan, Rachael Hwee Ling Sim +3Alignment-Aware Selection Shapley Value
Department of Computer Science, National University of Singapore, Singapore · Agency for Science, Technology and Research (A*STAR), Singapore
Let the Target Select for Itself: Data Selection via Target-Aligned Paths
May 10, 2026Huitao Yang, Hengzhi He, Tung Sum Thomas Kwok +1Alignment-Aware Selection Adaptive Sampling
University of California, Los Angeles
DARE: Difficulty-Adaptive Reinforcement Learning with Co-Evolved Difficulty Estimation
May 9, 2026Yang Zhou, Can Jin, Zihan Dong +7Large Language Model Reinforcement Learning Alignment-Aware Selection
Rutgers University · Amazon · Washington University +1
How to Utilize Failure Demo Data?: Effective Data Selection for Imitation Learning Using Distribution Differences in Attention Mechanism
May 8, 2026Kana Miyamoto, Kanata Suzuki, Tetsuya OgataImitation Learning Robotic Data Acquisition
Faculty of Science and Engineering, Waseda University, Tokyo, Japan · Physical AI Laboratory, Fujitsu Limited, Kanagawa, Japan
Wasserstein-Aligned Localisation for VLM-Based Distributional OOD Detection in Medical Imaging
May 6, 2026Bernhard Kainz, Johanna P Mueller, Matthew Baugh +1Medical Vision-Language Models Out-Of-Distribution Detection
Dept. AIBE, Friedrich–Alexander University Erlangen–Nürnberg, DE · Department of Computing, Imperial College London, UK · Technical University Munich, DE +1
Building informative materials datasets beyond targeted objectives
May 6, 2026Rafael Espinosa Castañeda, Ashley Dale, Hongchen Wang +6Data-Driven Materials Discovery Materials
Department of Materials Science and Engineering, University of Toronto, Canada. · 4Vector Institute for Artificial Intelligence, Toronto, Canada. · Department of Computer Science, Princeton University +2
What Makes Good Instruction-Tuning Data? An In-Context Learning Perspective
Apr 28, 2026Guangzeng Han, Xiaolei HuangInstruction Tuning Multimodal Continual Instruction Tuning
University of Memphis

Oct 1, 2026, cs.CVJ/K move · Enter open · S save

VASC: Value-Aware Sparse Attention with Cross-Layer Memory for Efficient 3D Reconstruction

Junyi Wu, Fanqing Kong, Leyang Chen, Shaoqiu Zhang+1

Shanghai Jiao Tong University

3D Reconstruction Visual Geometry Grounded Transformer Self-Supervised Vision Transformers Alignment-Aware Selection

Open paper AskPDF arXiv

Feed-forward 3D vision models such as VGGT have achieved remarkable progress, unifying camera estimation and dense scene reconstruction in a single pass. However, their quadratic global attention makes long image sequences expensive, while existing sparse methods may favor highly attended yet value-redundant regions. To address these limitations, we introduce VASC, a training-free sparse attention method combining value-aware block selection and execution-aware cross-layer memory. Our value-aware block selection integrates pooled query--key relevance with neighboring value contrast, reducing redundancy while preserving query-relevant and distinctive content. Cross-layer memory tracks unserved demand across layers and updates this state according to actual execution, enabling previously underserved blocks to compete under a fixed computation budget. Experiments on 7Scenes and NeuralRGB-D with VGGT and

π^3

demonstrate improved pose estimation and reconstruction quality compared with FasterVGGT, together with up to

2.29\times

faster inference than dense VGGT. Code is available at https://github.com/kosakayamahoo-design/VASC.

Momentum

Related topics

Latest papers 37