Is Multilingual LLM Watermarking Truly Multilingual? A Simple Back-Translation Solution
Paper • 2510.18019 • Published • 18
LLM Research
-
-
PORTool: Tool-Use LLM Training with Rewarded Tree
Paper • 2510.26020 • Published • 5 -
POWSM: A Phonetic Open Whisper-Style Speech Foundation Model
Paper • 2510.24992 • Published • 4 -
Ming-Flash-Omni: A Sparse, Unified Architecture for Multimodal Perception and Generation
Paper • 2510.24821 • Published • 41 -
Generalization or Memorization: Dynamic Decoding for Mode Steering
Paper • 2510.22099 • Published • 4 -
Omni-Reward: Towards Generalist Omni-Modal Reward Modeling with Free-Form Preferences
Paper • 2510.23451 • Published • 28 -
ARC-Encoder: learning compressed text representations for large language models
Paper • 2510.20535 • Published • 8 -
Continuous Autoregressive Language Models
Paper • 2510.27688 • Published • 74 -
Can Visual Input Be Compressed? A Visual Token Compression Benchmark for Large Multimodal Models
Paper • 2511.02650 • Published • 10 -
RADLADS: Rapid Attention Distillation to Linear Attention Decoders at Scale
Paper • 2505.03005 • Published • 36 -
Titans: Learning to Memorize at Test Time
Paper • 2501.00663 • Published • 31 -
DualPath: Breaking the Storage Bandwidth Bottleneck in Agentic LLM Inference
Paper • 2602.21548 • Published • 50 -
In-Context Reinforcement Learning for Tool Use in Large Language Models
Paper • 2603.08068 • Published • 43 -
OpenClaw-RL: Train Any Agent Simply by Talking
Paper • 2603.10165 • Published • 151 -
Pushing the Frontier of Audiovisual Perception with Large-Scale Multimodal Correspondence Learning
Paper • 2512.19687 • Published • 3 -
GradMem: Learning to Write Context into Memory with Test-Time Gradient Descent
Paper • 2603.13875 • Published • 35