paper-with-me

Papers Form

“Form” 태그가 달린 논문 1,618편 · 필터 해제

FreeAudio: Training-Free Timing Planning for Controllable Long-Form Text-to-Audio Generation

2025-07-11 · YuXuan Jiang, Zehua Chen, Zeqian Ju, Chang Li 외

Text-to-audio (T2A) generation has achieved promising results with the recent advances in generative models. However, because of the limited quality and quantity of temporally-aligned audio-text pairs, existing T2A metho…

Audio GenerationData AugmentationForm

Controlled Retrieval-augmented Context Evaluation for Long-form RAG

2025-06-24 · Jia-Huei Ju, Suzan Verberne, Maarten de Rijke, Andrew Yates

Retrieval-augmented generation (RAG) enhances large language models by incorporating context retrieved from external knowledge sources. While the effectiveness of the retrieval module is typically evaluated with relevanc…

DiagnosticFormRAGRetrieval+1

FormGym: Doing Paperwork with Agents

2025-06-17 · Matthew Toles, Rattandeep Singh, Isaac Song Zhou Yu

Completing paperwork is a challenging and time-consuming problem. Form filling is especially challenging in the pure-image domain without access to OCR, typeset PDF text, or a DOM. For computer agents, it requires multip…

FormInformation RetrievalOptical Character Recognition (OCR)

FreeQ-Graph: Free-form Querying with Semantic Consistent Scene Graph for 3D Scene Understanding

2025-06-16 · Chenlu Zhan, Gaoang Wang, Hongwei Wang

Semantic querying in complex 3D scenes through free-form language presents a significant challenge. Existing 3D scene understanding methods use large-scale training data and CLIP to align text queries with 3D semantic fe…

FormGraph GenerationRelational ReasoningScene Understanding

Direct Reasoning Optimization: LLMs Can Reward And Refine Their Own Reasoning for Open-Ended Tasks

2025-06-16 · Yifei Xu, Tusher Chakraborty, Srinagesh Sharma, Leonardo Nunes 외

Recent advances in Large Language Models (LLMs) have showcased impressive reasoning abilities in structured tasks like mathematics and programming, largely driven by Reinforcement Learning with Verifiable Rewards (RLVR),…

FormMath

ARGUS: Hallucination and Omission Evaluation in Video-LLMs

2025-06-09 · Ruchit Rawal, Reza Shirkavand, Heng Huang, Gowthami Somepalli 외

Video large language models have not yet been widely deployed, largely due to their tendency to hallucinate. Typical benchmarks for Video-LLMs rely simply on multiple-choice questions. Unfortunately, VideoLLMs hallucinat…

DescriptiveFormHallucinationMultiple-choice+2

LLM Unlearning Should Be Form-Independent

2025-06-09 · Xiaotian Ye, Mengqi Zhang, Shu Wu

Large Language Model (LLM) unlearning aims to erase or suppress undesirable knowledge within the model, offering promise for controlling harmful or private information to prevent misuse. However, recent studies highlight…

FormLarge Language Model

Writing-RL: Advancing Long-form Writing via Adaptive Curriculum Reinforcement Learning

2025-06-06 · Xuanyu Lei, Chenliang Li, Yuning Wu, Kaiming Liu 외

Recent advances in Large Language Models (LLMs) have enabled strong performance in long-form writing, yet existing supervised fine-tuning (SFT) approaches suffer from limitations such as data saturation and restricted le…

FormScheduling

Toward Better SSIM Loss for Unsupervised Monocular Depth Estimation

2025-06-05 · Yijun Cao, Fuya Luo, YongJie Li

Unsupervised monocular depth learning generally relies on the photometric relation among temporally adjacent images. Most of previous works use both mean absolute error (MAE) and structure similarity index measure (SSIM)…

Depth EstimationFormMonocular Depth EstimationSSIM+1

Unpacking Let Alone: Human-Scale Models Generalize to a Rare Construction in Form but not Meaning

2025-06-04 · Wesley Scivetti, Tatsuya Aoyama, Ethan Wilcox, Nathan Schneider

Humans have a remarkable ability to acquire and understand grammatical phenomena that are seen rarely, if ever, during childhood. Recent evidence suggests that language models with human-scale pretraining data may posses…

Form

SuperWriter: Reflection-Driven Long-Form Generation with Large Language Models

2025-06-04 · Yuhao Wu, Yushi Bai, Zhiqiang Hu, Juanzi Li 외

Long-form text generation remains a significant challenge for large language models (LLMs), particularly in maintaining coherence, ensuring logical consistency, and preserving text quality as sequence length increases. T…

FormText Generation

Fifteen Years of Child-Centered Long-Form Recordings: Promises, Resources, and Remaining Challenges to Validity

2025-06-04 · Loann Peurey, Marvin Lavechin, Tarek Kunze, Manel Khentout 외

Audio-recordings collected with a child-worn device are a fundamental tool in child language research. Long-form recordings collected over whole days promise to capture children's input and production with minimal observ…

Form

Automated Web Application Testing: End-to-End Test Case Generation with Large Language Models and Screen Transition Graphs

2025-06-03 · Nguyen-Khang Le, Quan Minh Bui, Minh Ngoc Nguyen, Hiep Nguyen 외

Web applications are critical to modern software ecosystems, yet ensuring their reliability remains challenging due to the complexity and dynamic nature of web interfaces. Recent advances in large language models (LLMs) …

FormScript Generation

Brain-Like Processing Pathways Form in Models With Heterogeneous Experts

2025-06-03 · Jack Cook, Danyal Akarca, Rui Ponte Costa, Jascha Achterberg

The brain is made up of a vast set of heterogeneous regions that dynamically organize into pathways as a function of task demands. Examples of such pathways can be seen in the interactions between cortical and subcortica…

FormMixture-of-Experts

Do Language Models Think Consistently? A Study of Value Preferences Across Varying Response Lengths

2025-06-03 · Inderjeet Nair, Lu Wang

Evaluations of LLMs' ethical risks and value inclinations often rely on short-form surveys and psychometric tests, yet real-world use involves long-form, open-ended responses -- leaving value-related risks and preference…

FormSpecificity

Self-supervised Latent Space Optimization with Nebula Variational Coding

2025-06-02 · Yida Wang, David Joseph Tan, Nassir Navab, Federico Tombari

Deep learning approaches process data in a layer-by-layer way with intermediate (or latent) features. We aim at designing a general solution to optimize the latent manifolds to improve the performance on classification, …

FormMetric LearningVariational Inference

ExpertLongBench: Benchmarking Language Models on Expert-Level Long-Form Generation Tasks with Structured Checklists

2025-06-02 · Jie Ruan, Inderjeet Nair, Shuyang Cao, Amy Liu 외

This paper introduces ExpertLongBench, an expert-level benchmark containing 11 tasks from 9 domains that reflect realistic expert workflows and applications. Beyond question answering, the application-driven tasks in Exp…

BenchmarkingFormQuestion Answering

FormFactory: An Interactive Benchmarking Suite for Multimodal Form-Filling Agents

2025-06-02 · Bobo Li, Yuheng Wang, Hao Fei, Juncheng Li 외

Online form filling is a common yet labor-intensive task involving extensive keyboard and mouse interactions. Despite the long-standing vision of automating this process with "one click", existing tools remain largely ru…

BenchmarkingForm

NexusSum: Hierarchical LLM Agents for Long-Form Narrative Summarization

2025-05-30 · Hyuntak Kim, Byung-Hak Kim

Summarizing long-form narratives--such as books, movies, and TV scripts--requires capturing intricate plotlines, character interactions, and thematic coherence, a task that remains challenging for existing LLMs. We intro…

DescriptiveFormLong-Form Narrative Summarization

Beyond Multiple Choice: Evaluating Steering Vectors for Adaptive Free-Form Summarization

2025-05-30 · Joschka Braun, Carsten Eickhoff, Seyed Ali Bahrainian

Steering vectors are a lightweight method for controlling text properties by adding a learned bias to language model activations at inference time. So far, steering vectors have predominantly been evaluated in multiple-c…

FormLanguage ModelingLanguage ModellingMultiple-choice
1–20 / 1,618 다음 →