Post-Training

Follow this topic Ask about this topic

Recent momentum

-12%

15 papers in the last 28 days · 0.4% 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 2026-09-14

7 new papers

A weekly snapshot of new work published in Post-Training.

Period ending 2026-09-07

8 new papers

A weekly snapshot of new work published in Post-Training.

139 papers

Latest in Post-Training

Open your feed →

LOCUS: Task-Aware Low-Rank Post-Training for Token-Efficient Language Generation
Sep 12, 2026Dongfang ZhaoLarge Language Model Post-Training Length
Post-Training Zero-Shot TTS for Fine-Grained Emotion and Duration Control via Natural Language
Sep 11, 2026Lianru Gao, Yujie Guo, Yong QinText-To-Speech Emotion Recognition
Scaling Post-Training Ternarisation to Qwen3-8B Capability Retention, Reproduction, Lossless Packing, and Packed Execution
Sep 10, 2026Anirudh Malik, M Sparsh Mehra, Poojith DevanLarge Language Model Scale Post-Training Pipelines
Data-Centric Post-Training for Financial Reasoning: Mining, Distillation, and Verifiable Learning
Sep 9, 2026Zhirayr Hayrapetyan, Andrei Kalmykov, Denis Kokosinskii +2Finance Domain Post-Training
Direct Diversity Optimization for Diverse Successful Trajectories in Preference Post-Training
Sep 9, 2026Junwon Ko, Dong-Jae Lee, Minchan Kwon +2Post-Training Sequential Decision Making
NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness
Sep 8, 2026NeoHorse Team, Guoliang Cao, Guohao Dai +34Self-Improving Agents Reinforcement Learning Post-Training
Router Prior Bias: Preserving Base Routing Structure in MoE Post-Training
Sep 8, 2026Jaedeok Lee, Keonwoo Kim, Dongyoon Han +3Mixture-Of-Expert Routing Post-Training
Beyond Shallow Alignment: How Post-Training Methods Determine Refusal Circuits And Steering Robustness
Sep 3, 2026Hoang Cuong Nguyen, Mark Dras, Usman NaseemRefusals Large Language Model Alignment
Post-Training Ternarization of Qwen3-4B Capability, Effective Bit Budget, Storage Compression, and Deployment
Sep 2, 2026Anirudh Malik, M Sparsh Mehra, Poojith DevanQwen3 Small Large Language Models
SCULPT: Training Edge Vision Models for Post-Training Quantization Readiness
Sep 1, 2026Bharadwaj Kavuri, Sourav Babu-PK, Varadhraj Ellapan +2Post-Training Quantization Quantization
From Production Traffic to Post-Training: Building a Self-Hosted LLM That Covers the Corporate Request Mix
Sep 1, 2026Olga Tsymboi, Dmitrii Stoianov, Ramil Latypov +11Large Language Model Serving Dialogue Benchmarks
Post-Training Science for Supervised Fine-Tuning
Sep 1, 2026Charles O'Neill, Mudith Jayasekara, Harry PartridgeSupervised Fine-Tuning Post-Training
Context-Grounding Gains Are Mediated by Pre-existing Machinery: Auditing GRPO, SFT, and DPO
Sep 1, 2026Prakhar Gupta, Vaibhav GuptaContextual Grounding Large Language Model Post-Training
LLM Post-Training as Brownfield Maintenance: An Industrial Perspective on Dataware Engineering
Aug 31, 2026Gopi Krishnan Rajbahadur, Amir M. Ebrahimi, Boyuan Chen +1Post-Training AI Code Generation
InspectorGPT: A Comparative Reasoning Enhanced VLM for Comprehensive Industrial Anomaly Detection
Aug 30, 2026Weifei Chen, Honghao Zhang, Zhiyuan You +1Multimodal Industrial Anomaly Detection Unsupervised Detectors
Decoding-Level Taboo: A Diagnostic Stress Test for LLM Robustness
Aug 10, 2026Tadanobu Chuyo Kamijo, Ori Rottenstreich, Javier Conde +2Large Language Model Safety Large Language Model Evaluation
CrystalGRPO: Target-Aligned and Coverage-Preserving Reinforcement Learning for Flow-Based Crystal Structure Prediction
Aug 6, 2026Kaixiang Su, Hongfei Xue, Qiang ZhuCrystal Structure Prediction Crystal
Sample-Adaptive Latent Rewards for Uncertainty-Guided Diffusion Post-Training
Aug 6, 2026Rui Li, Yuanzhi Liang, Ke Hao +4Uncertainty-Aware Teachers Latent Space
One Qubit Can Beat One Bit: Quantum Advantage for Post-Training Quantization
Aug 5, 2026Yuma Ichikawa, Moeto MishimaQuantization Quantum
Wnuan: Staged Post-Training for Question Answering over Proprietary Enterprise Knowledge
Aug 3, 2026Xiaofeng Shi, Xiaosong Qiu, Wenxin Ma +6Qwen3 Question
Post-Training on Office Work Improves Software Engineering: A Behavioral Account of Cross-Domain Transfer
Aug 3, 2026Logan Ritchie, Sushant Mehta, Liudas Panavas +1Long-Horizon Agents Post-Training
When Unlearning Fails: Reliable Data Deletion under Post-Training in Agent Networks
Jul 30, 2026Zihao Ding, Jun Huang, Liang DongMachine Unlearning Unlearning Aims
MixFrag: Fragility-Guided Mixed-Precision Post-Training Quantization for Vision Transformers
Jul 30, 2026Md. Mehrab Hossain Opi, Robiul Islam Ryad, Md. Umar FarukMixed-Precision Quantization Self-Supervised Vision Transformers
Compliance2LoRA: Personalizable On-Demand Safety Alignment on Arbitrary Policy Subsets via Hypernetwork-Generated LoRA Adapters
Jul 30, 2026Pankayaraj Pathmanathan, Furong HuangSafety Alignment Large Language Model Adaptation
SDO: Structure-Aware Data Organization for Efficient LLM Post-Training
Jul 29, 2026Jinliang Gao, Ning Yang, Hai Wang +2Post-Training Large Language
Post-Training at the Edge of Detectability: A Game-Theoretic Approach to Fine-Tuning
Jul 29, 2026Keegan Harris, Brian W. Lee, Ian Waudby-Smith +3Reinforcement Fine-Tuning Kullback-Leibler Regularization
Similar Models Learn Differently: Final-Window Pretraining Shapes Post-Training Beyond SFT
Jul 27, 2026Cen Lu, Yung-Chen Tang, Andrea CavallaroModel Checkpoints Post-Training
The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation
Jul 27, 2026Tianyi Men, Zhuoran Jin, Kang Liu +1Long-Horizon Planning On-Policy Distillation
Training Language Models to Cooperate with Inference-Time Controllers
Jul 26, 2026Moumita Choudhury, Vanshaj Khattar, Jing Liu +4Inference-Time Control Protein Language Model
Self-Boosting Vision-Language Models with Noisy Student On-Policy Self-Distillation
Jul 25, 2026Shuai Wang, Daoan Zhang, Zhe Tang +2Recent Vision-Language Models Unsupervised On-Policy Self-Distillation
Filling Before Advancing: Capability-Gap-Driven Post-Training for Scenario-Specialized Remote Sensing MLLMs
Jul 24, 2026Yuheng Zong, Minghua Wang, Xin Zhao +3Remote Sensing Multimodal Pretraining
Post-Training in Time Series Foundation Models: A Unifying Framework
Jul 22, 2026Shifeng Xie, Ambroise Odonnat, Zehao Xiao +7Time Series Foundation Models Wireless Foundation Models
Distilled Reinforcement Learning for LLM Post-training
Jul 19, 2026Chen Wang, Zhaochun Li, Jionghao Bai +4Reinforcement Learning Post-Training Large Language Model Post-Training
JoyNexus: Service-Oriented Multi-Tenant Post-Training for VLA Models
Jul 17, 2026Haoran Sun, Wentao Zhang, Junyang Hua +18Diffusion-Based Vision-Language-Actions Vision-Language-Action
Post-Training Shifts Confidence: A Three-Stage Analysis of How SFT, RL, and OPD Shape Pre-, Intra-, and Post-CoT Calibration
Jul 15, 2026Shuhao Li, Guodong Du, Anhao Zhao +3Confidence Estimation Post-Training
Exploring Post-Training Alignment of Small Language Models for Biomedical Data-to-Text Generation: A Case Study of Medication Leaflet
Jul 15, 2026Xi Yang, Guodong Liu, Chuqin Li +10Large Language Model Alignment Natural Language Datasets
Where Should RL Post-Training Compute Go? Model Size, Search, Learning, and Feedback
Jul 15, 2026Patrick Wilhelm, Odej KaoReinforcement Learning Post-Training Post-Training
Proxy Exploration and Reusable Guidance: A Modular LLM Post-Training Paradigm via Proxy-Guided Update Signals
Jul 13, 2026Daocheng Fu, Rong Wu, Yu Yang +7Reinforcement Learning Post-Training Large Language Model Post-Training
Post-Training in End-to-End Autonomous Driving
Jul 9, 2026Ruining Yang, Muxing Wang, Yixiao Chen +8Autonomous Driving Post-Training
HELP: Human-Efficient Large-Scale Robot Post-Training with Rollout Segmentation
Jul 8, 2026Shaopeng Zhai, Qi Zhang, Tianyi Zhang +5Vision-Language-Action Humanoid Robots
HiFA4: Training-Free 4-bit FlashAttention on Ascend HIF4 NPUs for LLM Inference
Jul 5, 2026Hui Dong, Yanzhao Li, Jie Gao +5LLM Inference Efficiency Matrix Multiplication
Aligning Language Models with Selective Prediction
Jul 3, 2026Gaoxiang Luo, Yifan Wu, Sinian Zhang +2Large Language Model Alignment Large Language Model Reliability
AutoTrainess: Teaching Language Models to Improve Language Models Autonomously
Jun 30, 2026Zhaojian Yu, Penghao Yin, Shuzheng Gao +3Protein Language Model Large Language Model Agents
A Novel Latent-Class Attack and its Detection by Class Subspace Orthogonalization
Jun 27, 2026Guangmingmei Yang, David J. Miller, George KesidisNovel Latent-Class Attack Backdoor Attacks
NormGuard: Reward-Preserving Norm Constraints in Flow-Matching Reinforcement Learning
Jun 26, 2026Tianlin Pan, Lianyu Pang, Cheng Da +4Reward Gradients Normalized Momentum
Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents
Jun 24, 2026Changdae Oh, Wendi Li, Seongheon Park +3Reinforcement Learning Post-Training Large Language Model Agents
OracleAnalyser: Analysing Implicit Semantics of Oracle Bone Scripts through MLLMs with Post-training
Jun 24, 2026Zijia Song, Yelin Wang, Zhengyi Ma +5Oracles Table Reasoning Datasets
The Interplay of Harness Design and Post-Training in LLM Agents
Jun 24, 2026Kyungmin Kim, Youngbin Choi, Seoyeon Lee +3Large Language Model Agents Tool-Schema Quality Predicts Tool Use
Understanding Knowledge Distillation in Post-Training: When It Helps and When It Fails
Jun 22, 2026Xin Liu, Simin Ma, Shujian Liu +5Heterogeneous Knowledge Distillation Post-Training
World Engine: Towards the Era of Post-Training for Autonomous Driving
Jun 18, 2026Tianyu Li, Li Chen, Caojun Wang +16Autonomous Driving Naturalistic Driving Data
Which Pairs to Compare for LLM Post-Training?
Jun 17, 2026Jiangze Han, Vineet Goyal, Will MaLarge Language Model Post-Training Post-Training
Repeated post-training is not Self-improving: Diagnosing Scientific Amnesia in Continual DPO Pipelines
Jun 17, 2026Jianzhe Lin, Fei Wang, Xiaolin Li +2Catastrophic Forgetting Post-Training
EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts
Jun 17, 2026Minseo Kim, Minjae Lee, Seunghyuk Oh +7Reinforcement Learning Rollouts Long Rollouts
Learning task-specific subspaces via interventional post-training of speech foundation models
Jun 16, 2026Jack Cox, Jon BarkerSelf-Supervised Speech Models Contrastive Learning
Beyond the GUI Paradigm: Do Mobile Agents Need the Phone Screen?
Jun 16, 2026Li Gu, Zihuan Jiang, Linqiang Guo +6Graphical User Interface Post-Training
How Post-Training Shapes Biological Reasoning Models
Jun 15, 2026Lukas Fesser, Hanlin Zhang, Michelle M. Li +5Biological Large Reasoning Models
AudioDER: A Deduplication-Enhanced Reasoning Dataset for Post-Training Large Audio-Language Models
Jun 12, 2026Hui Geng, Yi Su, Han Yin +7Large Audio Language Models Table Reasoning Datasets
OdysSim: Building Foundation Models for Human Behavior Simulation
Jun 12, 2026Xuhui Zhou, Weiwei Sun, Weihua Du +6Social Simulations Behavioral Foundation Models
Can Post-Training Turn LLMs into Good Medical Coders? An Empirical Study of Generative ICD Coding
Jun 11, 2026Ziqing Wang, Weihao Li, Shijie Chen +2International Classification Of Disease Codes AI Code Generation
Select and Improve: Understanding the Mechanics of Post-Training for Reasoning
Jun 11, 2026Akshay Krishnamurthy, Audrey Huang, Nived RajaramanReinforcement Learning Post-Training Large Reasoning Models

Sep 12, 2026 · cs.CLJ/K move · Enter open · S save

LOCUS: Task-Aware Low-Rank Post-Training for Token-Efficient Language Generation

Dongfang Zhao

Large language model serving costs scale directly with output sequence length, yet standard preference alignment often inflates response verbosity without improving utility. We study whether the parameterization of post-training updates affects generation length: low-rank subspaces alter sequence length without modifying the alignment loss. We present LOCUS, a method that selects a task-aware low-rank adaptation subspace to minimize output-token cost subject to a utility constraint. Within this subspace, post-training retains the native preference objective with a frozen backbone. Across Anthropic HH-RLHF dialogue preferences, we evaluate two

\sim

3B decoder backbones, Pythia-2.8B and Qwen2.5-3B, against protocol-matched full-parameter DPO and DrDPO branches and the released SamPO checkpoint. LOCUS reduces continuation length by up to 39.84% on Pythia-2.8B and by 14.87--17.58% on Qwen2.5-3B while updating only 0.24--0.28% of model parameters, with no material change in the internal preference diagnostic.

Large Language Model Post-Training Length Post-Training Chatbots

Open paper Ask about it PDF