Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes Paper • 2608.05000 • Published 4 days ago • 53
ArcMemo: Abstract Reasoning Composition with Lifelong LLM Memory Paper • 2509.04439 • Published Sep 4, 2025 • 2
TS-Reasoner: Aligning Time Series Foundation Models with LLM Reasoning Paper • 2510.03519 • Published Oct 3, 2025 • 1
FlowBank: Query-Adaptive Agentic Workflows Optimization through Precompute-and-Reuse Paper • 2606.11290 • Published Jun 9 • 2
ArrowGEV: Grounding Events in Video via Learning the Arrow of Time Paper • 2601.06559 • Published Apr 16 • 1
LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks Paper • 2608.01964 • Published 6 days ago • 161
Reinforcement Learning with Evolving Rubrics as Rewards for Audio Reasoning Paper • 2608.02831 • Published 5 days ago • 7
ArrowGEV: Grounding Events in Video via Learning the Arrow of Time Paper • 2601.06559 • Published Apr 16 • 1
FlowBank: Query-Adaptive Agentic Workflows Optimization through Precompute-and-Reuse Paper • 2606.11290 • Published Jun 9 • 2
TS-Reasoner: Aligning Time Series Foundation Models with LLM Reasoning Paper • 2510.03519 • Published Oct 3, 2025 • 1
TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning Paper • 2607.08940 • Published Jul 9 • 2
ArcMemo: Abstract Reasoning Composition with Lifelong LLM Memory Paper • 2509.04439 • Published Sep 4, 2025 • 2