SOTAVerified

8k

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–25 of 202 papers

TitleStatusHype
MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent—0
UltraVideo: High-Quality UHD Video Dataset with Comprehensive Captions—0
Through the Valley: Path to Effective Long CoT Training for Small Language Models—0
InterRVOS: Interaction-aware Referring Video Object Segmentation—0
SynthRL: Scaling Visual Reasoning with Verifiable Data Synthesis—0
LLM in the Loop: Creating the PARADEHATE Dataset for Hate Speech Detoxification—0
Efficient Neural and Numerical Methods for High-Quality Online Speech Spectrogram Inversion via Gradient Theorem—0
LoLA: Low-Rank Linear Attention With Sparse Caching—0
GeoLLaVA-8K: Scaling Remote-Sensing Multimodal Large Language Models to 8K ResolutionCode1
Efficient Correlation Volume Sampling for Ultra-High-Resolution Optical Flow Estimation—0
UHD Image Dehazing via anDehazeFormer with Atmospheric-aware KV Cache—0
MMLongBench: Benchmarking Long-Context Vision-Language Models Effectively and ThoroughlyCode2
Achieving Scalable Robot Autonomy via neurosymbolic planning using lightweight local LLMCode0
ViCTr: Vital Consistency Transfer for Pathology Aware Image Synthesis—0
Effective Length Extrapolation via Dimension-Wise Positional Embeddings Manipulation—0
KeyDiff: Key Similarity-Based KV Cache Eviction for Long-Context LLM Inference in Resource-Constrained Environments—0
FactGuard: Leveraging Multi-Agent Systems to Generate Answerable and Unanswerable Questions for Enhanced Long-Context LLM ExtractionCode0
Sequential-NIAH: A Needle-In-A-Haystack Benchmark for Extracting Sequential Needles from Long Contexts—0
Pan-LUT: Efficient Pan-sharpening via Learnable Look-Up Tables—0
Visual Acuity Consistent Foveated Rendering towards Retinal Resolution—0
XL-Instruct: Synthetic Data for Cross-Lingual Open-Ended Generation—0
ESSR: An 8K@30FPS Super-Resolution Accelerator With Edge Selective Network—0
Video-XL-Pro: Reconstructive Token Compression for Extremely Long Video Understanding—0
KL3M Tokenizers: A Family of Domain-Specific and Character-Level Tokenizers for Legal, Financial, and Preprocessing ApplicationsCode0
SkyLadder: Better and Faster Pretraining via Context Window SchedulingCode1
Show:102550
← PrevPage 1 of 9Next →

No leaderboard results yet.