The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping Paper • 2604.11297 • Published 5 days ago • 135
Generating Physically Stable and Buildable LEGO Designs from Text Paper • 2505.05469 • Published May 8, 2025 • 29
DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models Paper • 2603.26164 • Published 22 days ago • 353
Nemotron-Math: Efficient Long-Context Distillation of Mathematical Reasoning from Multi-Mode Supervision Paper • 2512.15489 • Published Dec 17, 2025 • 12
GEditBench v2: A Human-Aligned Benchmark for General Image Editing Paper • 2603.28547 • Published 18 days ago • 32
BandPO: Bridging Trust Regions and Ratio Clipping via Probability-Aware Bounds for LLM Reinforcement Learning Paper • 2603.04918 • Published Mar 5 • 56
HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding Paper • 2601.14724 • Published Jan 21 • 75
EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience Paper • 2601.15876 • Published Jan 22 • 92
FutureOmni: Evaluating Future Forecasting from Omni-Modal Context for Multimodal LLMs Paper • 2601.13836 • Published Jan 20 • 37
ABC-Bench: Benchmarking Agentic Backend Coding in Real-World Development Paper • 2601.11077 • Published Jan 16 • 67
DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI Paper • 2512.16676 • Published Dec 18, 2025 • 222
Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm Paper • 2511.04570 • Published Nov 6, 2025 • 242
MetaMind: Modeling Human Social Thoughts with Metacognitive Multi-Agent Systems Paper • 2505.18943 • Published May 25, 2025 • 25