arXiv:2603. 12478v2 Announce Type: replace-cross Abstract: Multimodal instruction tuning is often compute-inefficient because training budgets are spread across large mixed image-video pools whose utility is highly uneven.
arXiv:2606. 28551v1 Announce Type: cross Abstract: Building performant Vision-Language Models (VLMs) requires carefully curating large-scale training datasets, yet the community lacks systematic benchmarks for evaluating such curation strategies.
arXiv:2607. 24570v1 Announce Type: cross Abstract: Large-scale video platforms process millions of uploads hourly, requiring moderation systems that can localize when and where policy violations occur within each video.
arXiv:2609.16059v1 Announce Type: cross Abstract: Multimodal instruction following (MMIF) is crucial for building generalist agents. However, current training paradigms rely heavily on Supervised Fin...
LeVJEPA is a video encoder that eliminates the need for architectural asymmetries, exponential-moving-average target encoders, stop-gradients, and capacity-limited predictors used in prior self‑supervised methods. It trains a single encoder with an invariance loss over global and local views, regularized by SIGReg to prevent collapse, and achieves strong performance with far less pretraining compute. The approach also allows block‑causal attention, making temporal ordering a property of the encoder itself, and matches or surpasses state‑of‑the‑art baselines on both appearance‑centric and motion‑centric benchmarks.
Token-Budget Distillation (TBD) is a parameter‑efficient fine‑tuning framework that adapts video vision‑language models to a fixed token budget. It freezes the pretrained backbone, updates only LoRA adapters, and incorporates FlashVID visual token compression. TBD uses a dual‑path teacher‑student design with full‑token supervision and compressed student optimization, enabling the student to recover full‑token semantics while remaining efficient under aggressive token reduction.
arXiv:2608. 08961v1 Announce Type: new Abstract: AI training's rising resource intensity is straining electricity supplies and carbon budgets, motivating systematic study of memory-efficient training on constrained hardware.
arXiv:2510. 09608v2 Announce Type: replace-cross Abstract: Vision-language models (VLMs) could power real-time assistants and autonomous agents, but they face a critical challenge: understanding near-infinite video streams without escalating latency and memory usage.
arXiv:2608.22869v1 Announce Type: cross Abstract: While Vision-Language-Action (VLA) models have leveraged internet-scale pretraining and task-focused finetuning to achieve strong performance on long...
PRISM is a training‑free framework that efficiently selects visual instruction data for multimodal large language models by addressing the anisotropy in visual feature distributions, which causes a Global Semantic Drift. By implicitly re‑centering visual semantics, PRISM removes the influence of global background features, cutting data‑selection and model‑tuning time to 30% of conventional pipelines while improving performance across eight multimodal and three language benchmarks, achieving a 101.7% relative gain over baseline models.
The study investigates how long‑video language models decide which frames to keep, compress, and reuse, testing each decision in isolation across six selection rules, three benchmarks, and two answering models. It finds that selecting frames based on queries yields the biggest performance boost, that halving spatial resolution costs little, and that reallocating saved tokens to more compressed frames can further improve accuracy. The work also highlights the importance of a unified evaluation harness to avoid misleading comparisons.
arXiv:2608. 03979v1 Announce Type: cross Abstract: We introduce Video-DeepResearch (Video-DR), extending multimodal agents from static images to continuous video streams, a setting that demands dense spatiotemporal grounding coupled with open-web exploration.
TT-VidT is a video pretraining method that decouples the temporal axis by combining a per‑frame ViT-B/16 spatial encoder with a compact Temporal Transfer Layer trained via Diff Compression. The authors conduct a systematic 24‑configuration study to isolate architecture, objective, and decoder effects, showing that the full TT-VidT design yields the strongest motion‑sensitive representations. In downstream fine‑tuning, TT‑VidT outperforms state‑of‑the‑art baselines on Jester, Something‑Something V2, ARID, and Diving48 while using significantly fewer encoder FLOPs.