English
Related papers

Related papers: From Patches to Trajectories: Privileged Process S…

200 papers

Large Language Models (LLMs) are changing the coding paradigm, known as vibe coding, yet synthesizing algorithmically sophisticated and robust code still remains a critical challenge. Incentivizing the deep reasoning capabilities of LLMs is…

Computation and Language · Computer Science 2026-02-18 Chansung Park , Juyong Jiang , Fan Wang , Sayak Paul , Jiasi Shen , Jing Tang , Jianguo Li

Semi-supervised learning (SSL) has achieved significant progress by leveraging both labeled data and unlabeled data. Existing SSL methods overlook a common real-world scenario when labeled data is extremely scarce, potentially as limited as…

Computer Vision and Pattern Recognition · Computer Science 2025-04-15 Hezhao Liu , Yang Lu , Mengke Li , Yiqun Zhang , Shreyank N Gowda , Chen Gong , Hanzi Wang

Adapting Large Language Models (LLMs) to a continuous stream of tasks is a critical yet challenging endeavor. While Parameter-Efficient Fine-Tuning (PEFT) methods have become a standard for this, they face a fundamental dilemma in continual…

Machine Learning · Computer Science 2025-11-11 Haeyong Kang

Multi-Agent Path Finding (MAPF) is an NP-hard problem with applications in warehouse automation and multi-robot coordination. Learning-based MAPF solvers offer fast and scalable planning but often produce feasible trajectories that contain…

Robotics · Computer Science 2026-01-29 Yimin Tang , Sven Koenig , Erdem Bıyık

While large language models (LLMs) have advanced the development of general-purpose agents, achieving robust generalization to unseen tasks remains a significant challenge. Current approaches typically rely on either fine-tuning or…

Artificial Intelligence · Computer Science 2026-03-20 Thomas Palmeira Ferraz , Romain Deffayet , Vassilina Nikoulina , Hervé Déjean , Stéphane Clinchant

We introduce the notion of a Patch Sampling Schedule (PSS), that varies the number of Vision Transformer (ViT) patches used per batch during training. Since all patches are not equally important for most vision objectives (e.g.,…

Computer Vision and Pattern Recognition · Computer Science 2022-08-23 Bradley McDanel , Chi Phuong Huynh

While critical for alignment, Supervised Fine-Tuning (SFT) incurs the risk of catastrophic forgetting, yet the layer-wise emergence of instruction-following capabilities remains elusive. We investigate this mechanism via a comprehensive…

Machine Learning · Computer Science 2026-04-15 Qinghua Zhao , Xueling Gong , Xinyu Chen , Zhongfeng Kang , Xinlu Li

Fast domain adaptation remains a fundamental challenge for deploying multi-agent systems across diverse environments in Vehicle-to-Everything (V2X) collaborative perception. Despite the success of Parameter-Efficient Fine-Tuning (PEFT) in…

Computer Vision and Pattern Recognition · Computer Science 2026-04-08 Zesheng Jia , Jin Wang , Siao Liu , Lingzhi Li , Ziyao Huang , Yunjiang Xu , Jianping Wang

Deploying Transformer-based large language models (LLMs) on resource-constrained edge devices for long-sequence tasks remains challenging due to the quadratic time complexity of self-attention and growing Key-Value (KV) cache demands. While…

A recurring challenge in preference fine-tuning (PFT) is handling $\textit{intransitive}$ (i.e., cyclic) preferences. Intransitive preferences often stem from either $\textit{(i)}$ inconsistent rankings along a single objective or…

Machine Learning · Computer Science 2026-05-07 Jiahao Zhang , Lujing Zhang , Keltin Grimes , Zhuohao Yu , Gokul Swamy , Zhiwei Steven Wu

The problem of piecewise affine (PWA) regression and planning is of foundational importance to the study of online learning, control, and robotics, where it provides a theoretically and empirically tractable setting to study systems…

Machine Learning · Statistics 2024-03-20 Adam Block , Max Simchowitz , Russ Tedrake

Code agents resolve 65-70% of SWE-bench Verified issues, but Pass@1 cannot tell us why the rest fail, and, as we show, capable-model failures are systematically misdiagnosed without trajectory data. We introduce TRAJEVAL, a training-free…

Parameter-efficient fine-tuning (PEFT) methods have shown promise in adapting large language models, yet existing approaches exhibit counter-intuitive phenomena: integrating router into prompt tuning (PT) increases training efficiency yet…

Computation and Language · Computer Science 2025-05-15 Zongqian Li , Yixuan Su , Nigel Collier

Supervised fine-tuning (SFT) provides the standard approach for teaching LLMs new behaviors from offline expert demonstrations. However, standard SFT uniformly fits all samples -- including those with low likelihood under the base model --…

Machine Learning · Computer Science 2026-05-15 Mahdi Sabbaghi , George Pappas , Adel Javanmard , Hamed Hassani

Progress in Multiple Object Tracking (MOT) has been historically limited by the size of the available datasets. We present an efficient framework to annotate trajectories and use it to produce a MOT dataset of unprecedented size. In our…

Computer Vision and Pattern Recognition · Computer Science 2017-03-23 Santiago Manen , Michael Gygli , Dengxin Dai , Luc Van Gool

Large reasoning models such as DeepSeek-R1 and their distilled variants achieve strong performance on complex reasoning tasks. Yet, distilling these models often demands large-scale data for supervised fine-tuning (SFT), motivating the…

Computation and Language · Computer Science 2026-01-16 Lechen Zhang , Yunxiang Zhang , Wei Hu , Lu Wang

Supervised fine-tuning (SFT) is the predominant method for adapting large language models (LLMs), yet it often struggles with generalization compared to reinforcement learning (RL). In this work, we posit that this performance disparity…

Computation and Language · Computer Science 2026-02-03 Rui Ming , Haoyuan Wu , Shoubo Hu , Zhuolun He , Bei Yu

Multimodal dataset distillation aims to construct compact synthetic datasets that enable efficient compression and knowledge transfer from large-scale image-text data. However, existing approaches often fail to capture the complex,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-27 Shengbin Guo , Hang Zhao , Senqiao Yang , Chenyang Jiang , Yuhang Cheng , Xiangru Peng , Rui Shao , Zhuotao Tian

The cosine similarity between a large language model's hidden activations before and after Supervised Fine-Tuning (SFT) remains very high. This, at first glance, suggests that SFT leaves the model's activation geometry largely undisturbed.…

Artificial Intelligence · Computer Science 2026-05-13 Ruhaan Chopra

Parameter-efficient fine-tuning (PEFT) allows model builders to capture the task-specific parameters into adapters, which are a fraction of the size of the original base model. Popularity of PEFT technique for fine-tuning has led to the…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-10-24 Saransh Gupta , Umesh Deshpande , Travis Janssen , Swami Sundararaman