SOTAVerified

Language Modeling

Papers

Showing 9761000 of 14182 papers

TitleStatusHype
STING-BEE: Towards Vision-Language Model for Real-World X-ray Baggage Security InspectionCode1
LLM Social Simulations Are a Promising Research Method0
Prompt Optimization with Logged Bandit Data0
TiC-LM: A Web-Scale Benchmark for Time-Continual LLM PretrainingCode1
A Survey of Scaling in Large Language Model Reasoning0
When Reasoning Meets Compression: Benchmarking Compressed Large Reasoning Models on Complex Reasoning Tasks0
BioAtt: Anatomical Prior Driven Low-Dose CT Denoising0
STPNet: Scale-aware Text Prompt Network for Medical Image SegmentationCode1
Prompt-Reverse Inconsistency: LLM Self-Inconsistency Beyond Generative Randomness and Prompt Paraphrasing0
LLM-VPRF: Large Language Model Based Vector Pseudo Relevance Feedback0
Biomedical Question Answering via Multi-Level Summarization on a Local Knowledge Graph0
Investigating and Scaling up Code-Switching for Multilingual Language Model Pre-TrainingCode0
LLM-mediated Dynamic Plan Generation with a Multi-Agent Approach0
TransforMerger: Transformer-based Voice-Gesture Fusion for Robust Human-Robot Communication0
Representation Bending for Large Language Model SafetyCode1
When Persuasion Overrides Truth in Multi-Agent LLM Debates: Introducing a Confidence-Weighted Persuasion Override Rate (CW-POR)0
Unleashing the Power of Pre-trained Encoders for Universal Adversarial Attack Detection0
VerifiAgent: a Unified Verification Agent in Language Model ReasoningCode0
Multi-Token Attention0
Command A: An Enterprise-Ready Large Language Model0
Detecting PTSD in Clinical Interviews: A Comparative Analysis of NLP Methods and Large Language Models0
Automated detection of atomicity violations in large-scale systems0
ShieldGemma 2: Robust and Tractable Image Content Moderation0
4th PVUW MeViS 3rd Place Report: Sa2VACode5
CrowdVLM-R1: Expanding R1 Ability to Vision Language Model for Crowd Counting using Fuzzy Group Relative Policy RewardCode1
Show:102550
← PrevPage 40 of 568Next →

No leaderboard results yet.