Papers 2k
“2k” 태그가 달린 논문 288편 · 필터 해제
MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization
Vector Quantized Variational Autoencoders (VQ-VAEs) are fundamental models that compress continuous visual data into discrete tokens. Existing methods have tried to improve the quantization strategy for better reconstruc…
2kImage GenerationImage ReconstructionQuantizationMGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization
Vector Quantized Variational Autoencoders (VQ-VAEs) are fundamental models that compress continuous visual data into discrete tokens. Existing methods have tried to improve the quantization strategy for better reconstruc…
2kQuantizationUnderstanding and Improving Length Generalization in Recurrent Models
Recently, recurrent models such as state space models and linear attention have become popular due to their linear complexity in the sequence length. Thanks to their recurrent nature, in principle they can process arbitr…
2kState Space ModelsA strengthened bound on the number of states required to characterize maximum parsimony distance
In this article we prove that the distance $d_{\mathrm{MP}}(T_1,T_2) = k$ between two unrooted binary phylogenetic trees $T_1, T_2$ on the same set of taxa can be defined by a character that is convex on one of $T_1, T_2…
2kStructured Variational $D$-Decomposition for Accurate and Stable Low-Rank Approximation
We introduce the $D$-decomposition, a non-orthogonal matrix factorization of the form $A \approx P D Q$, where $P \in \mathbb{R}^{n \times k}$, $D \in \mathbb{R}^{k \times k}$, and $Q \in \mathbb{R}^{k \times n}$. The de…
2kLatent Wavelet Diffusion: Enabling 4K Image Synthesis for Free
High-resolution image synthesis remains a core challenge in generative modeling, particularly in balancing computational efficiency with the preservation of fine-grained visual detail. We present Latent Wavelet Diffusion…
2k4kComputational EfficiencyDenoising+1Tradeoffs between Mistakes and ERM Oracle Calls in Online and Transductive Online Learning
We study online and transductive online learning when the learner interacts with the concept class only via Empirical Risk Minimization (ERM) or weak consistency oracles on arbitrary instance subsets. This contrasts with…
2kSegment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language Models
Enhancing the reasoning capabilities of large language models effectively using reinforcement learning (RL) remains a crucial challenge. Existing approaches primarily adopt two contrasting advantage estimation granularit…
2k4kGSM8KReinforcement Learning (RL)Test-Time Training Done Right
Test-Time Training (TTT) models context dependencies by adapting part of the model's weights (referred to as fast weights) during inference. This fast weight, akin to recurrent states in RNNs, stores temporary memories o…
2kNovel View SynthesisMMP-2K: A Benchmark Multi-Labeled Macro Photography Image Quality Assessment Database
Macro photography (MP) is a specialized field of photography that captures objects at an extremely close range, revealing tiny details. Although an accurate macro photography image quality assessment (MPIQA) metric can b…
2kDiversityImage Quality AssessmentTwin-2K-500: A dataset for building digital twins of over 2,000 people based on their answers to over 500 questions
LLM-based digital twin simulation, where large language models are used to emulate individual human behavior, holds great promise for research in AI, social science, and digital experimentation. However, progress in this…
2kBenchmarkingPIIvot: A Lightweight NLP Anonymization Framework for Question-Anchored Tutoring Dialogues
Personally identifiable information (PII) anonymization is a high-stakes task that poses a barrier to many open-science data sharing initiatives. While PII identification has made large strides in recent years, in practi…
2kUnlocking the Potential of Difficulty Prior in RL-based Multimodal Reasoning
In this work, we investigate how explicitly modeling problem's difficulty prior information shapes the effectiveness of reinforcement learning based fine-tuning for multimodal reasoning. Our exploration mainly comprises …
2kMathematical ReasoningMultimodal ReasoningUIShift: Enhancing VLM-based GUI Agents through Self-supervised Reinforcement Learning
Training effective Vision Language Models (VLMs) for GUI agents typically relies on supervised fine-tuning (SFT) over large-scale annotated datasets, where the collection process is labor-intensive and error-prone. In th…
2kReinforcement Learning (RL)ViMRHP: A Vietnamese Benchmark Dataset for Multimodal Review Helpfulness Prediction via Human-AI Collaborative Annotation
Multimodal Review Helpfulness Prediction (MRHP) is an essential task in recommender systems, particularly in E-commerce platforms. Determining the helpfulness of user-generated reviews enhances user experience and improv…
2kRecommendation SystemsCalibrating Translation Decoding with Quality Estimation on LLMs
Neural machine translation (NMT) systems typically employ maximum a posteriori (MAP) decoding to select the highest-scoring translation from the distribution mass. However, recent evidence highlights the inadequacy of MA…
2kMachine TranslationNMTTranslationaiXamine: Simplified LLM Safety and Security
Evaluating Large Language Models (LLMs) for safety and security remains a complex task, often requiring users to navigate a fragmented landscape of ad hoc benchmarks, datasets, metrics, and reporting formats. To address …
2kAdversarial RobustnessFairnessHallucination+2Turbo2K: Towards Ultra-Efficient and High-Quality 2K Video Synthesis
Demand for 2K video synthesis is rising with increasing consumer expectations for ultra-clear visuals. While diffusion transformers (DiTs) have demonstrated remarkable capabilities in high-quality video generation, scali…
2kKnowledge DistillationTransfer LearningVideo GenerationOn Linear Representations and Pretraining Data Frequency in Language Models
Pretraining data has a direct impact on the behaviors and quality of language models (LMs), but we only understand the most basic principles of this relationship. While most work focuses on pretraining data's effect on d…
2kIn-Context LearningRelationRethinking the Generation of High-Quality CoT Data from the Perspective of LLM-Adaptive Question Difficulty Grading
Recently, DeepSeek-R1 (671B) (DeepSeek-AIet al., 2025) has demonstrated its excellent reasoning ability in complex tasks and has publiclyshared its methodology. This provides potentially high-quality chain-of-thought (Co…
2kCode GenerationMath