SAGE: From Direct Answering to Evidence-Grounded Inference for Chinese Ancient Document Understanding
arXiv:2608.24011v1 Announce Type: cross Abstract: Chinese ancient document understanding demands complex visual, linguistic, and historical reasoning. Current Large Vision-Language Models…
AeroDPO: Unleashing Lightweight UAV Navigation with High-Fidelity Perception and Automated Preference Optimization
arXiv:2608.07557v2 Announce Type: replace-cross Abstract: Vision-Language Navigation for Unmanned Aerial Vehicles (UAV-VLN) requires rapid and reactive control in complex 3D…
Hybrid Semantic Tool Discovery for Enterprise MCP Gateway: Architecture and Implementation
arXiv:2608.23992v1 Announce Type: cross Abstract: Large language model (LLM) agents invoke external tools to retrieve and reason over information beyond…
OPDSearch+: On-Policy Distillation with RL Refinement for Search-Augmented Reasoning
arXiv:2608.24310v1 Announce Type: new Abstract: Search-augmented reasoning remains difficult for small language models. On-policy distillation (OPD) from trained teachers offers…
Mechanistic Circuit Identification for Controllable Data Generation
arXiv:2608.24065v1 Announce Type: cross Abstract: While recent advances in data synthesis aim to curate high-quality datasets, most generation pipelines still…
ORBITALIF: An Efficient Spiking Federated Learning Framework for Onboard Cloud Removal
arXiv:2608.24073v1 Announce Type: cross Abstract: Low-earth-orbit (LEO) satellites enable high-resolution, large-scale Earth observation for applications such as disaster monitoring and…
Cross-Domain, Multi-Task Data-to-Text Generation without In-Domain Training Data
arXiv:2608.23391v2 Announce Type: replace-cross Abstract: Structured data exists in many forms (tables, knowledge graphs, charts, and time series), and converting…
LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding
arXiv:2607.24555v2 Announce Type: replace-cross Abstract: Serving large language models at long context is bottlenecked by the key-value (KV) cache, which…
VideoHarness-RSI: Recursive Harness Self-Improvement for Long-Video Understanding with Frozen Vision-Language Models
arXiv:2608.24302v1 Announce Type: new Abstract: Long-video understanding depends critically on how a limited model context is constructed from a much…