arXiv Machine Learning

LookThere! Sparse Vision by Reinforced Selection

LookThere! Sparse Vision by Reinforced Selection proposes an end‑to‑end reinforcement learning framework that jointly trains a shallow input selector and a deep representation extractor for vision transformers. The selector learns where to focus and the extractor learns what to process, enabling the model to use only a tiny fraction of the input tokens—down to 0.2%—while preserving accuracy. The method outperforms existing selection techniques across diverse tasks and models, including high‑resolution recognition, segmentation, zero‑shot classification, and regression, establishing a new Pareto frontier in performance‑compute trade‑offs.

Hugging Face Trending Papers
Aug 6

Evidence-Driven Dynamic Visual Selector for Efficient Long Video Understanding

Recent advancements in MLLM-based long-form video understanding have mitigated inference-time computational cost and limited context lengths by selecting query-relevant frames. However, existing approaches predominantly rely on external proxy scorers and rigid heuristic rules, inevitably suffering from misalignment with the target MLLM's intrinsic evidence and failing to accommodate the non-uniform spatiotemporal information density.

arXiv AI
Aug 28

PACE: A Unified Condense-and-Extract Paradigm for Fast VLM Inference

PACE introduces a training‑free Condense‑and‑Extract framework that speeds up Vision‑Language Model inference by first adaptively downsampling visual inputs before encoding and then selectively retaining essential tokens during decoding. The Adaptive Pixel Compressor (APC) reduces encoder workload while preserving global context, and the Dynamic Dual‑Attention Extractor (DDAE) keeps task‑critical details by fusing visual and language signals. Applied to Qwen2.5‑VL‑7B, PACE maintains 93.8% of performance using only 10% of visual tokens, achieving a 3.1× speedup in time to first token.

By Junjie Liu, Shengyuan Ye, Xu Chen
arXiv Computer Vision
Aug 27

FLEET: Token-Based Feature Extraction for Event Camera-based Reinforcement Learning

FLEET is a token‑based feature extractor that processes event camera data directly, using random Fourier features and cross‑attention to compress variable‑length event streams into fixed‑size latent representations. By decoupling inference cost from sensor resolution, it avoids the high compute and temporal blurring associated with CNN‑based grid aggregation. Experiments on a new high‑throughput benchmark show that FLEET outperforms state‑of‑the‑art methods and remains robust across different observation frequencies.

By Tristan Gottwald, Maximilian Schier, Melanie Schaller, Bodo Rosenhahn
arXiv AI
Aug 26

Rethinking Pre-Training and Augmentation for Zero-Shot Cross-City Object Detection

The paper proposes a modular training pipeline for zero‑shot cross‑city object detection that combines a multi‑dataset pre‑training strategy with class‑agnostic objectness distillation and a domain‑resilient augmentation stream featuring a Grayworld transformation. Applied to the RF‑DETR detector, the approach reduces cross‑city distribution gaps while using only 16 GB GPU memory, achieving a 24.29‑point mAP improvement and 1st place on the AI City Challenge Track 6 leaderboard. The authors provide code and data at the referenced GitHub repository.

By Long Hoang Pham, Quoc Pham-Nam Ho, Huy-Hung Nguyen, Duong Nguyen-Ngoc Tran, Ngoc Doan-Minh Huynh, Cu Quoc Le, Hoang-Khang Nguyen, Hyung-Min Jeon, Chi Dai Tran, Son Hong Phan, Duong Khac Vu, Trinh Le Ba Khanh, Jae Wook Jeon
Hugging Face Trending Papers
Aug 19

Falcon Perception-HD: High Density Perception via Reinforcement Learning

Falcon Perception-HD applies reinforcement learning (GRPO) to autoregressive perception models, aligning them directly with precision and recall metrics rather than relying on maximum‑likelihood fine‑tuning. The RL framework introduces reward design for set‑structured outputs and multi‑head sampling control, enabling state‑of‑the‑art performance in very dense scenes (up to 500 objects) and eliminating common issues such as mask repetitions, NMS, and coordinate deduplication. Hybrid self‑annotation pipelines tailored for difficult referring expressions and dense scenes further boost RL training, with improvements observed across all difficulty levels on PBench and SACO‑Gold, and the model preserves object existence knowledge without negative samples.

arXiv AI
Aug 5

Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch Agent

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.

By Zhen Fang, Yu Zeng, Wenxuan Huang, Yiming Zhao, Shiting Huang, Tianfei Ren, Qi Lu, Qingnan Ren, Qisheng Su, Lionel Z. Wang, Qingyu Yin, Shuang Chen, Zehui Chen, Lin Chen, Zhenfei Yin, Yao Hu, Shaohui Lin, Wanli Ouyang, Shaosheng Cao, Feng Zhao
arXiv Computer Vision
Sep 3

Towards Zero-Shot Transfer Across Embodiments For Driving VLAs

The paper investigates how Vision‑Language‑Action (VLA) models can generalise across different driving environments and camera setups. It introduces a multi‑dataset training strategy and an auxiliary objective called BEV‑Forcing, which injects bird‑eye‑view spatial information into the VLA backbone to improve both in‑distribution and out‑of‑distribution performance on a limited number of camera rigs. The authors observe that while BEV‑Forcing helps when training data is scarce, its advantage diminishes as the number of training embodiments grows, suggesting that scaling diversity may reduce the impact of such auxiliary tasks.

By Caio Azevedo, Stefano Sabatini, Sascha Hornauer, Fabien Moutarde
arXiv Machine Learning
Jul 20

More with Less: a Large Scale Remote Sensing VLM with a Simple Recipe

arXiv:2607. 15942v1 Announce Type: cross Abstract: Remote sensing vision-language models are increasingly expected to support open-ended reasoning over Earth Observation data and a variety of tasks.

By Stefan Maria Ailuro (INSAIT, Sofia University "St. Kliment Ohridski"), Mario Markov (INSAIT, Sofia University "St. Kliment Ohridski"), Mohammad Mahdi (INSAIT, Sofia University "St. Kliment Ohridski"), Luc Van Gool (INSAIT, Sofia University "St. Kliment Ohridski"), Danda Pani Paudel (INSAIT, Sofia University "St. Kliment Ohridski")