…reliable training targets. Beyond depth and point maps, ViGeo also predicts surface normals within the same framework. Trained solely on public datasets, ViGeo achieves state-of-the-art performance across online, offline…
…schema, joinability, unionability, grounding 🔗 TRL-Rbench — multi-target row prediction (50 subtasks, 123 targets) + record linkage (16 datasets) 🌊 TRL-DLTE — a 47,772-table data-lake enrichment pipeline spanning all three granularities…
…MoE consistently outperforms training the target architecture from scratch under the same training budget. Second, different one-shot expert compression methods converge to similar final performance after large-scale continual pretraining. Motivated…
…Stochastic Condition Masking (SCM) randomly partitions modalities into clean conditions and noisy targets during training, enabling omni-directional conditional generation instead of fixed mappings. Decoupled Gated LoRA (DGL) introduces per-modality LoRAs…
…By scaling and directly adding the clean source video latent to the noised target latent, this elegant design eliminates the need for token concatenation, drastically reducing computational cost while maintaining robust capabilities…
…TrackCraft3R achieves state-of-the-art performance on standard sparse and dense 3D tracking benchmarks, while running 1.3x faster and using 4.6x less peak memory than the strongest prior method…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct LLM agents increasingly retrieve externally curated skills-procedural instructions retrieved at decision time-to improve performance on long-horizon interactive tasks. Existing skill libraries…
…Across 11 image editing models, we find overall low performance, with the current highest-performing industry leader scoring only 17.1% (mIoU). Task decomposition reveals especially challenging operation types (geometric transformation, most…
…Lei Yang , , Abstract Multi-domain reinforcement learning in language models causes performance degradation through shared computational pathways, but targeted refresh and rollback techniques can selectively recover lost capabilities with minimal side effects…
…art performance in zero-shot transfer. AI-generated summary Domain Generalization (DG) aims to learn representations that remain robust under out-of-distribution (OOD) shifts and generalize effectively to unseen target domains…