Downstream Fine-Tuning

Follow this topic Ask about this topic

Recent momentum

-25%

3 papers in the last 28 days · 0.0% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this topic, kept on the site without email delivery.

Period ending 2026-09-21

1 new paper

A weekly snapshot of new work published in Downstream Fine-Tuning.

Period ending 2026-09-14

1 new paper

A weekly snapshot of new work published in Downstream Fine-Tuning.

Period ending 2026-09-07

1 new paper

A weekly snapshot of new work published in Downstream Fine-Tuning.

44 papers

Latest in Downstream Fine-Tuning

Browse all topics →

Judging by the Cover: Cleaning LLM Truthfulness Benchmarks to Avoid Surface-Level Feature Leakage
Sep 14, 2026Foad Namjoo, Remy Ogasawara, Amirali Abdullah +3Downstream Fine-Tuning
HERALD: High-Fidelity Exemplar Retrieval with Adaptive Landmark Distillation for Heterophily-Aware Graph Condensation
Sep 11, 2026Sujan Chakraborty, Priyanka Saha, Saptarshi BejText-Attributed Graph Heterogeneity
Good Pretraining, Bad SFT: Checkpoint Quality Across the Training Stack
Sep 8, 2026Sohir Maskey, Philipp Scholl, Jonas Knupp +2Model Pretraining Downstream Fine-Tuning
TokEval: A Tokenizer Evaluation Suite
Aug 18, 2026Clara MeisterTokenization Downstream Fine-Tuning
Geometric and Behavioral Stratification in Transformer Residual Streams
Aug 12, 2026Nelson GudaTransformer Residual Streams Residual Stream
Retrieval Augmented Biomedical Question Answering with Weak Question Recovery and Neural Reranking for BioASQ Task 14b
Aug 2, 2026Xueying Zhao, Lee Mai, Balaji AnandganeshReranking Text Corpora
FairDiffuseVQVAE: Sampling-Time Fairness in Tabular Diffusion via Conditional Refinement of Vector-Quantized Latents
Jul 31, 2026Nitish Nagesh, Mahdi Bagheri, Amir M. RahmaniFairness-Aware Learning Distributional Fidelity
PathSelect: Sequential Token Selection for Whole Slide Pathology
Jul 26, 2026Jingzhi Chen, Landi He, Zehong Chen +2Visual Token Pruning Downstream Fine-Tuning
Evaluating Federated Pre-Training: On the Reliability of Downstream Fine-Tuning and Intrinsic Evaluation
Jul 20, 2026Claudia Grosser, Maike Heuer, Denis Krompass +1Model Pretraining Downstream Fine-Tuning
Analyzing Image Encoder Choices and Graph Homophily in GCN Frameworks for Breast Ultrasound Classification
Jul 13, 2026Sabahattin Mert Daloglu, Ceren Coskun, Harvey Castro +2Mammography Ultrasound
Enhancing In-context Panoramic Generation via Geometric-aware Pretraining
Jul 9, 2026Haoran Feng, Ruiyang Zhang, Longyi Zhang +2Panoramic Images Panoptic Segmentation
GraphBU: MILP Instance Generation with Graph-Native Block Units
Jul 7, 2026Xiaolei Guo, Chenyu Zhou, Jianghao Lin +1Mixed-Integer Programming Downstream Fine-Tuning
Towards Evaluating Data Priors for Tabular Foundation Models
Jun 28, 2026Zeynep Türkmen, Kürşat Kaya, Alexander Pfefferle +1Tabular Foundation Models Prior Knowledge
High-Fidelity Synthetic Transmission Electron Microscopy Image Generation Using Diffusion Probabilistic Models for Data-Limited Semiconductor Metrology
Jun 23, 2026Johannes Boehm, Bappaditya DeyMedical Image Generation Transmission Electron Microscopy
MGUP: A Momentum-Gradient Alignment Update Policy for Stochastic Optimization
Jun 16, 2026Da Chang, Ganzhao YuanUpdates Stochastic Optimization
SoK: AI-Augmented Binary Reversing
Jun 16, 2026Yujeong Kwon, Yiyue Zhang, Shakhzod Yuldoshkhujaev +3Reverse Engineering Binary
Pre-Training for Simulation-Based Science: A Study on Jet Foundation Model Training Objectives
Jun 12, 2026Ibrahim Elsharkawy, Joschka Birk, Vinicius Mikuni +3Downstream Fine-Tuning Foundation Model
How do Self-Supervised Remote Sensing Vision Models Transfer to Downstream Tasks?
Jun 11, 2026Julia Romero, Qin Lv, Morteza KarimzadehGeospatial Foundation Models Vision Foundation Models
DUET -- Dual User Embedding Transformers for Offsite Conversion Prediction
Jun 8, 2026Reazul Hasan Russel, Mingwei Tang, Rostam Shirani +18Click-Through Rate Prediction Late-Stage Ranker
When Do Local Score Models Extrapolate Across Size? A Diagnostic Theory and Benchmark
Jun 8, 2026Wenjie XiLarge Behavior Model Extrapolation
Beyond Neural Collapse: Task-Intrinsic Geometry Governs Neural Representations in Modular Arithmetic
Jun 8, 2026Hu Tan, Kuo Gai, Shihua ZhangNeural Collapse Implicit Neural Representations
Leveraging Soft Distributions of SSL-Derived Discrete Speech Tokens for Downstream Inference
Jun 5, 2026Kentaro Onda, Satoru Fukayama, Daisuke Saito +1Downstream Fine-Tuning
Double Preconditioning (DoPr): Optimization for Test-Time Performance, not Validation Loss
Jun 4, 2026Thomas T. Zhang, Alok Shah, Yifei Zhang +3Downstream Fine-Tuning Loss Function
Where does Absolute Position come from in decoder-only Transformers?
Jun 4, 2026Valeria Ruscio, Umberto Nanni, Fabrizio SilvestriTransformer Encoder Rotary Position Embedding
From Layers to Submodules: Rethinking Granularity in Replacement-Based LLM Compression
Jun 1, 2026Elia Cunegatti, Marcus Vukojevic, Erik Nielsen +1Large Language Model Compression Downstream Fine-Tuning
Provable Data Scaling Law for Meta Learning via Complexity Minimization
Jun 1, 2026Kazuto Fukuchi, Ryuichiro Hataya, Kota MatsuiMeta-Learning Model Pretraining
ANDES: Agent Native Data Evolving Synthesis Tool for Autonomous Instruction Alignment
May 31, 2026Zhengyang Zhao, Shengjie Ye, Lu Ma +3Iterative Co-Training Artificial Intelligence Research
Activation Steering for Synthetic Data Generation: The Role of Diversity in Downstream Safety Detection
May 27, 2026Vijeta Deshpande, Tootiya Giyahchi, Veena Padmanabhan +2Activation Steering Synthetic Data
SuperValid: Capability-Aligned OOD Validation for Generalizable Downstream Scaling
May 27, 2026Quanen Sun, Changxin Tian, Ke Shi +6Downstream Fine-Tuning Out-Of-Distribution
ETCHR: Editing To Clarify and Harness Reasoning
May 22, 2026Beichen Zhang, Yuhong Liu, Jinsong Li +3Image Editing Visual Reasoning
AIGaitor: Privacy-preserving and cloud-free motion analysis for everyone, using edge computing
May 20, 2026Lauhitya Reddy, Trisha M. Kesar, Hyeokhyen KwonGait Recognition Motion Capture
Scalable Decision-Focused Learning through Cost-Sensitive Regression
May 18, 2026Noah Schutte, Senne Berden, Tias Guns +2Loss Function Downstream Fine-Tuning
$φ$ -Balancing for Mixture-of-Experts Training
May 14, 2026Lizhang Chen, Jonathan Li, Qi Wang +5Mixture-of-Experts Models Balanced Learning
What properties of reasoning supervision are associated with improved downstream model quality?
May 13, 2026Mikołaj Langner, Dzmitry Pihulski, Jan Eliasz +5Table Reasoning Datasets Downstream Fine-Tuning
On What We Can Learn from Low-Resolution Data
May 12, 2026Theresa Dahl Frehr, Niels Henrik Pontoppidan, Hiba Nassar +1Low-Resolution Downstream Fine-Tuning
Discriminative Span as a Predictor of Synthetic Data Utility via Classifier Reconstruction
May 10, 2026Radhika Amar Desai, Modigari NarendraSynthetic Data Vision Datasets
Mitigating Label Shift in Tabular In-Context Learning via Test-Time Posterior Adjustment
May 6, 2026Seunghan LeeTabular Foundation Models Tabpfn
Decision Boundary-aware Generation for Long-tailed Learning
May 2, 2026Jiacheng Yang, Ruichi Zhang, Chikai Shang +5Generative Adversarial Network Downstream Fine-Tuning
MemRouter: Memory-as-Embedding Routing for Long-Term Conversational Agents
May 1, 2026Tianyu Hu, Weikai Lin, Weizhi Zhang +2Long-Term Conversational Memory Memdefrag
Physics-Conditioned Synthesis of Internal Ice-Layer Thickness for Incomplete Layer Traces
Apr 22, 2026Zesheng Liu, Maryam RahnemoonfarSea-Surface Temperature Data Synthetic Aperture Radar
EgoVerse: An Egocentric Human Dataset for Robot Learning from Around the World
Apr 8, 2026Ryan Punamiya, Simar Kareer, Zeyi Liu +37Egocentric Dataset Scalable Robot Learning
On the Asymptotics of Self-Supervised Pre-training: Two-Stage M-Estimation and Representation Symmetry
Mar 29, 2026Mohammad Tinati, Stephen TuSelf-Supervised Model Pretraining
Patch the Distribution Mismatch: RL Rewriting Agent for Stable Off-Policy SFT
Feb 11, 2026Jiacheng Wang, Zhijie Liu, Ping Jian +4Supervised Fine-Tuning Rewrite
Bilevel Data Curation for LLM Fine-tuning: Offline Selection and Online Self-Refining Generation
Nov 26, 2025Quan Xiao, Yutong Xuan, Gaowen Liu +2Large Language Model Fine-Tuning Data-Curation

Sep 14, 2026 · cs.CLJ/K move · Enter open · S save

Judging by the Cover: Cleaning LLM Truthfulness Benchmarks to Avoid Surface-Level Feature Leakage

Foad Namjoo, Remy Ogasawara, Amirali Abdullah, Cullen Anderson+2

Binary-choice truth benchmarks ask models to choose between a correct and an incorrect answer, but if the two answers differ systematically in surface-level features, models can exceed chance without performing the intended reasoning. We show that this failure mode is detectable and can be exploited by downstream classifiers. In TruthfulQA, a simple six-feature logistic classifier achieves substantial accuracy in separating correct from incorrect answers. We further show that similar surface-level artifacts are present in additional benchmarks. To counteract this, we developed a general mechanism to clean them by removing the most leakage-reinforcing pairs. We release a version of TruthfulQA with surface-feature leakage reduced close to chance and provide a mechanism, Audit-Prune, so that the datasets can be cleaned before release.

Downstream Fine-Tuning

Open paper Ask about it PDF