paper-with-me

Papers 16k

“16k” 태그가 달린 논문 146편 · 필터 해제

UniCode$^2$: Cascaded Large-scale Codebooks for Unified Multimodal Understanding and Generation

2025-06-25 · Yanzhe Chen, Huasong Zhong, Yan Li, Zhenheng Yang

Unified multimodal large language models (MLLMs) have shown promise in jointly advancing multimodal understanding and generation, with visual codebooks discretizing images into tokens for autoregressive modeling. Existin…

16k

MSTAR: Box-free Multi-query Scene Text Retrieval with Attention Recycling

2025-06-12 · Liang Yin, Xudong Xie, Zhang Li, Xiang Bai 외

Scene text retrieval has made significant progress with the assistance of accurate text localization. However, existing approaches typically require costly bounding box annotations for training. Besides, they mostly adop…

16kRetrievalText Retrieval

How Far Are We from Optimal Reasoning Efficiency?

2025-06-08 · Jiaxuan Gao, Shu Yan, Qixin Tan, Lu Yang 외

Large Reasoning Models (LRMs) demonstrate remarkable problem-solving capabilities through extended Chain-of-Thought (CoT) reasoning but often produce excessively verbose and redundant reasoning traces. This inefficiency …

16kBenchmarkingNumerical Integration

FlashDMoE: Fast Distributed MoE in a Single Kernel

2025-06-05 · Osayamen Jonathan Aimuyo, Byungsoo Oh, Rachee Singh

The computational sparsity of Mixture-of-Experts (MoE) models enables sub-linear growth in compute cost as model size increases, thus offering a scalable path to training massive neural networks. However, existing implem…

16kCPUGPUMixture-of-Experts+1

FAMA: The First Large-Scale Open-Science Speech Foundation Model for English and Italian

2025-05-28 · Sara Papi, Marco Gaido, Luisa Bentivogli, Alessio Brutti 외

The development of speech foundation models (SFMs) like Whisper and SeamlessM4T has significantly advanced the field of speech processing. However, their closed nature--with inaccessible training data and code--poses maj…

16k

SpecExtend: A Drop-in Enhancement for Speculative Decoding of Long Sequences

2025-05-27 · Jungyoub Cha, Hyunjong Kim, Sungzoon Cho

Speculative decoding is a widely adopted technique for accelerating inference in large language models (LLMs), but its performance degrades on long inputs due to increased attention cost and reduced draft accuracy. We in…

16kLong-Context Understanding

UI-Genie: A Self-Improving Approach for Iteratively Boosting MLLM-based Mobile GUI Agents

2025-05-27 · Han Xiao, Guozhi Wang, Yuxiang Chai, Zimu Lu 외

In this paper, we introduce UI-Genie, a self-improving framework addressing two key challenges in GUI agents: verification of trajectory outcome is challenging and high-quality training data are not scalable. These chall…

16k

MonarchAttention: Zero-Shot Conversion to Fast, Hardware-Aware Structured Attention

2025-05-24 · Can Yaras, Alec S. Xu, Pierre Abillama, Changwoo Lee 외

Transformers have achieved state-of-the-art performance across various tasks, but suffer from a notable quadratic complexity in sequence length due to the attention mechanism. In this work, we propose MonarchAttention --…

16k4k

Training Long-Context LLMs Efficiently via Chunk-wise Optimization

2025-05-22 · Wenhao Li, Yuxin Zhang, Gen Luo, Daohai Yu 외

While long-context large language models (LLMs) exhibit remarkable document processing capabilities, their prohibitively high training costs often hinder customized applications. To mitigate this issue, we propose \texti…

16kGPU

PSC: Extending Context Window of Large Language Models via Phase Shift Calibration

2025-05-18 · Wenqiao Zhu, Chao Xu, Lulu Wang, Jun Wu

Rotary Position Embedding (RoPE) is an efficient position encoding approach and is widely utilized in numerous large language models (LLMs). Recently, a lot of methods have been put forward to further expand the context …

16kPosition

Achieving Scalable Robot Autonomy via neurosymbolic planning using lightweight local LLM

2025-05-13 · Nicholas Attolino, Alessio Capitanelli, Fulvio Mastrogiovanni

PDDL-based symbolic task planning remains pivotal for robot autonomy yet struggles with dynamic human-robot collaboration due to scalability, re-planning demands, and delayed plan availability. Although a few neurosymbol…

16k8kTask Planning

FalseReject: A Resource for Improving Contextual Safety and Mitigating Over-Refusals in LLMs via Structured Reasoning

2025-05-12 · Zhehao Zhang, Weijie Xu, Fanyou Wu, Chandan K. Reddy

Safety alignment approaches in large language models (LLMs) often lead to the over-refusal of benign queries, significantly diminishing their utility in sensitive scenarios. To address this challenge, we introduce FalseR…

16kBenchmarkingSafety Alignment

KL3M Tokenizers: A Family of Domain-Specific and Character-Level Tokenizers for Legal, Financial, and Preprocessing Applications

2025-03-21 · Michael J Bommarito, Daniel Martin Katz, Jillian Bommarito

We present the KL3M tokenizers, a family of specialized tokenizers for legal, financial, and governmental text. Despite established work on tokenization, specialized tokenizers for professional domains remain understudie…

16k4k8kOptical Character Recognition (OCR)

NSF-SciFy: Mining the NSF Awards Database for Scientific Claims

2025-03-11 · Delip Rao, Weiqiu You, Eric Wong, Chris Callison-Burch

We present NSF-SciFy, a large-scale dataset for scientific claim extraction derived from the National Science Foundation (NSF) awards database, comprising over 400K grant abstracts spanning five decades. While previous d…

16kAbstract generationClaim Verification

X-LRM: X-ray Large Reconstruction Model for Extremely Sparse-View Computed Tomography Recovery in One Second

2025-03-09 · Guofeng Zhang, Ruyi Zha, Hao He, Yixun Liang 외

Sparse-view 3D CT reconstruction aims to recover volumetric structures from a limited number of 2D X-ray projections. Existing feedforward methods are constrained by the limited capacity of CNN-based architectures and th…

16kCT Reconstruction

Evaluating the Suitability of Different Intraoral Scan Resolutions for Deep Learning-Based Tooth Segmentation

2025-02-26 · Daron Weekley, Jace Duckworth, Anastasiia Sukhanova, Ananya Jana

Intraoral scans are widely used in digital dentistry for tasks such as dental restoration, treatment planning, and orthodontic procedures. These scans contain detailed topological information, but manual annotation of th…

16k2k4k8k+2

EpMAN: Episodic Memory AttentioN for Generalizing to Longer Contexts

2025-02-20 · Subhajit Chaudhury, Payel Das, Sarathkrishna Swaminathan, Georgios Kollias 외

Recent advances in Large Language Models (LLMs) have yielded impressive successes on many language tasks. However, efficient processing of long contexts using LLMs remains a significant challenge. We introduce \textbf{Ep…

16kDecoderQuestion AnsweringRetrieval-augmented Generation

CLOVER: A Test Case Generation Benchmark with Coverage, Long-Context, and Verification

2025-02-12 · Jiacheng Xu, Bo Pang, Jin Qu, Hiroaki Hayashi 외

Software testing is a critical aspect of software development, yet generating test cases remains a routine task for engineers. This paper presents a benchmark, CLOVER, to evaluate models' capabilities in generating and c…

16k4ksoftware testing

Fairness through Difference Awareness: Measuring Desired Group Discrimination in LLMs

2025-02-04 · Angelina Wang, Michelle Phan, Daniel E. Ho, Sanmi Koyejo

Algorithmic fairness has conventionally adopted the mathematically convenient perspective of racial color-blindness (i.e., difference unaware treatment). However, we contend that in a range of important settings, group d…

16kDescriptiveFairness

M+: Extending MemoryLLM with Scalable Long-Term Memory

2025-02-01 · Yu Wang, Dmitry Krotov, Yuanzhe Hu, Yifan Gao 외

Equipping large language models (LLMs) with latent-space memory has attracted increasing attention as they can extend the context window of existing language models. However, retaining information from the distant past r…

16kGPULong-Context UnderstandingText Generation
1–20 / 146 다음 →