Papers 8k
“8k” 태그가 달린 논문 202편 · 필터 해제
MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent
Despite improvements by length extrapolation, efficient attention and memory modules, handling infinitely long documents with linear complexity without performance degradation during extrapolation remains the ultimate ch…
8kUltraVideo: High-Quality UHD Video Dataset with Comprehensive Captions
The quality of the video dataset (image quality, resolution, and fine-grained caption) greatly influences the performance of the video generation model. The growing demand for video applications sets higher requirements …
4k8kVideo GenerationThrough the Valley: Path to Effective Long CoT Training for Small Language Models
Long chain-of-thought (CoT) supervision has become a common strategy to enhance reasoning in language models. While effective for large models, we identify a phenomenon we call Long CoT Degradation, in which small langua…
8kReinforcement Learning (RL)InterRVOS: Interaction-aware Referring Video Object Segmentation
Referring video object segmentation aims to segment the object in a video corresponding to a given natural language expression. While prior works have explored various referring scenarios, including motion-centric or mul…
8kObjectReferring Video Object SegmentationSemantic Segmentation+3LLM in the Loop: Creating the PARADEHATE Dataset for Hate Speech Detoxification
Detoxification, the task of rewriting harmful language into non-toxic text, has become increasingly important amid the growing prevalence of toxic content online. However, high-quality parallel datasets for detoxificatio…
8kSynthRL: Scaling Visual Reasoning with Verifiable Data Synthesis
Vision-language models (VLMs) trained via reinforcement learning with verifiable reward (RLVR) have shown notable progress in scaling test-time compute effectively. In this work, we investigate how synthesized RL data ca…
8kMathVisual ReasoningEfficient Neural and Numerical Methods for High-Quality Online Speech Spectrogram Inversion via Gradient Theorem
Recent work in online speech spectrogram inversion effectively combines Deep Learning with the Gradient Theorem to predict phase derivatives directly from magnitudes. Then, phases are estimated from their derivatives via…
8kLoLA: Low-Rank Linear Attention With Sparse Caching
Transformer-based large language models suffer from quadratic complexity at inference on long sequences. Linear attention methods are efficient alternatives, however, they fail to provide an accurate approximation of sof…
4k8kGPUGeoLLaVA-8K: Scaling Remote-Sensing Multimodal Large Language Models to 8K Resolution
Ultra-high-resolution (UHR) remote sensing (RS) imagery offers valuable data for Earth observation but pose challenges for existing multimodal foundation models due to two key bottlenecks: (1) limited availability of UHR…
8kAvgEarth ObservationLarge Language Model+2Efficient Correlation Volume Sampling for Ultra-High-Resolution Optical Flow Estimation
Recent optical flow estimation methods often employ local cost sampling from a dense all-pairs correlation volume. This results in quadratic computational and memory complexity in the number of pixels. Although an altern…
8kOptical Flow EstimationUHD Image Dehazing via anDehazeFormer with Atmospheric-aware KV Cache
In this paper, we propose an efficient visual transformer framework for ultra-high-definition (UHD) image dehazing that addresses the key challenges of slow training speed and high memory consumption for existing methods…
4k8kComputational EfficiencyGPU+2MMLongBench: Benchmarking Long-Context Vision-Language Models Effectively and Thoroughly
The rapid extension of context windows in large vision-language models has given rise to long-context vision-language models (LCVLMs), which are capable of handling hundreds of images with interleaved text tokens in a si…
8kBenchmarkingRAGAchieving Scalable Robot Autonomy via neurosymbolic planning using lightweight local LLM
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 PlanningViCTr: Vital Consistency Transfer for Pathology Aware Image Synthesis
Synthesizing medical images remains challenging due to limited annotated pathological data, modality domain gaps, and the complexity of representing diffuse pathologies such as liver cirrhosis. Existing methods often str…
8kData AugmentationImage GenerationEffective Length Extrapolation via Dimension-Wise Positional Embeddings Manipulation
Large Language Models (LLMs) often struggle to process and generate coherent context when the number of input tokens exceeds the pre-trained length. Recent advancements in long-context extension have significantly expand…
8kPositionKeyDiff: Key Similarity-Based KV Cache Eviction for Long-Context LLM Inference in Resource-Constrained Environments
We demonstrate that geometrically distinctive keys during LLM inference tend to have high attention scores. Based on the phenomenon we propose KeyDiff, a training-free KV cache eviction method based solely on key similar…
8kFactGuard: Leveraging Multi-Agent Systems to Generate Answerable and Unanswerable Questions for Enhanced Long-Context LLM Extraction
Extractive reading comprehension systems are designed to locate the correct answer to a question within a given text. However, a persistent challenge lies in ensuring these models maintain high accuracy in answering ques…
8kData AugmentationReading ComprehensionSequential-NIAH: A Needle-In-A-Haystack Benchmark for Extracting Sequential Needles from Long Contexts
Evaluating the ability of large language models (LLMs) to handle extended contexts is critical, particularly for retrieving information relevant to specific queries embedded within lengthy inputs. We introduce Sequential…
8kPan-LUT: Efficient Pan-sharpening via Learnable Look-Up Tables
Recently, deep learning-based pan-sharpening algorithms have achieved notable advancements over traditional methods. However, many deep learning-based approaches incur substantial computational overhead during inference,…
8kComputational EfficiencyGPUVisual Acuity Consistent Foveated Rendering towards Retinal Resolution
Prior foveated rendering methods often suffer from a limitation where the shading load escalates with increasing display resolution, leading to decreased efficiency, particularly when dealing with retinal-level resolutio…
8k