Reward models (RMs) provide critical feedback signals for LLM post-training, notably in reinforced fine-tuning (RFT) and reinforcement learning (RL) pipelines. However, current reward evaluation relies on heterogeneous criteria such as rule-based verifiers, ground-truth references, procedural checklists, and complex rubrics, where a unified mechanism to integrate all types of evidence remains unexplored.
Classical reinforcement learning (RL) typically seeks a deterministic policy that maximizes the expected sum of a scalar reward. Yet, modern applications such as language model fine-tuning or scientific discovery demand diversity.
This paper investigates rubric-aware, multitask fine-tuning of transformer models for automated grading of introductory C++ programming assignments, with the goal of producing grade predictions that better reflect instructor grading behavior than general-purpose LLMs. Using multi-semester CS1 data, student submissions are paired with numeric scores, letter-grade buckets, and assignment rubrics, then preprocessed into unified sequences for transformer input.
Consistency training encourages a model to produce similar outputs across related inputs or sampling procedures. Such methods are simple, scalable, and largely label-free, but their effects on model alignment remain poorly understood.
Multi-modal Large Language Models (MLLMs) achieve strong performance on vision-language tasks, but incorporating visual inputs through a vision encoder (e. g.
We present BaltiVoice, a 16. 8-hour read-speech corpus for Balti (ISO 639-3: bft), a Tibetic language spoken in Gilgit-Baltistan, Pakistan, with no prior publicly available ASR resources.
While Large Language Models (LLMs) excel in code generation, they remain prone to replicating subtle yet critical vulnerabilities endemic to their training data. Current alignment techniques, such as Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), typically apply coarse-grained optimization at the sequence level.
Large language models (LLMs) are increasingly evaluated in multilingual settings, yet their inference behavior in low-resource African languages remains underexplored especially under pure prompting without fine-tuning. We present a systematic study of prompting strategies for Natural Language Inference (NLI) in Swahili, Yoruba, and Hausa using the AfriXNLI benchmark.
arXiv:2606. 01151v1 Announce Type: new Abstract: Behavior cloning with high-capacity generative policies achieves strong imitation performance, but is often limited by demonstration coverage and distribution shift.
By Hikmet Simsir, Ozgur S. Oguz
arXiv:2603. 00963v2 Announce Type: replace Abstract: While reinforcement learning (RL) has been central to the recent success of large language models (LLMs), RL optimization is notoriously unstable, especially when compared to supervised fine-tuning (SFT).
By Hongzhan Chen, Tao Yang, Yuhua Zhu, Shiping Gao, Xiaojun Quan, Ting Yao
arXiv:2606. 02341v1 Announce Type: cross Abstract: Underwater acoustic classification has a wide array of oceanic applications, but faces challenges due to an increasingly complex acoustic environment.
By Amirmohammad Mohammadi, Joshua Peeples, Alexandra Van Dine
arXiv:2606. 00616v1 Announce Type: cross Abstract: Recent Vision-Language Models (VLMs) struggle with grounded reasoning, temporal consistency, and context aware planning in videos.
By Shivam Singh, Saptarshi Majumdar, Pratik Prabhanjan, Zicheng Liu, Emad Barsoum
arXiv:2601. 03309v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models, which integrate pretrained large Vision-Language Models (VLM) into their policy backbone, are gaining significant attention for their promising generalization capabilities.
By Jianke Zhang, Xiaoyu Chen, Qiuyue Wang, Mingsheng Li, Yanjiang Guo, Yucheng Hu, Jiajun Zhang, Shuai Bai, Junyang Lin, Jianyu Chen
arXiv:2606. 01062v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models have become a leading approach for decoupling parameter count from computational cost in large language models, yet effectively scaling MoE performance remains a challenge.
By Jiarui Feng, Hanqing Zeng, Karish Grover, Ruizhong Qiu, Yinglong Xia, Qiang Zhang, Qifan Wang, Ren Chen, Dongqi Fu, Jiayi Liu, Zhoukai Zhao, Xiangjun Fan, Benyu Zhang, Yixin Chen
arXiv:2601. 07177v5 Announce Type: replace-cross Abstract: Federated learning (FL) addresses privacy and data-silo issues in the training of large language models (LLMs).
By Mingxiang Tao, Yu Tian, Wenxuan Tu, Yue Yang, Xue Yang, Xiangyan Tang
arXiv:2606. 00831v1 Announce Type: new Abstract: Subliminal learning is a phenomenon where language models can transmit behavioral traits to other models through seemingly innocuous data (Cloud et al.
By Todd Nief, Harvey Yiyun Fu, Mark Muchane, Ari Holtzman
arXiv:2602. 07083v2 Announce Type: replace-cross Abstract: Structural modeling is a fundamental component of computational engineering science, in which even minor physical inconsistencies or specification violations may invalidate downstream simulations.
By Yongqing Jiang, Jianze Wang, Zhiqi Shen, Zhenghong Lin, Jiayuan Wang, Yijian Yang, Kaoshan Dai, Haoran Luo
arXiv:2606. 02194v1 Announce Type: new Abstract: Distilling expert demonstration data into large generative models using behavioral cloning is a scalable approach to learning capable policies for robotic control, particularly for dexterous manipulation.
By Christian Scherer, Joe Watson, Theo Gruner, Daniel Palenicek, Ingmar Posner, Jan Peters
arXiv:2606. 00944v1 Announce Type: new Abstract: Applying differential privacy (DP) via DP-SGD to Low-Rank Adaptation (LoRA) is a natural approach for privacy-preserving fine-tuning.
By Shihao Wang, Xueru Zhang
arXiv:2606. 01909v1 Announce Type: cross Abstract: We present Echo, a proof-of-concept audio system built around a single 25 M-parameter ViT encoder.
By Louis Mouchon