arXiv Computer Vision
TRACE: Trajectory-robust Admission with Evidence Ordering for Efficient GUI Agents
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Sep 23
From Token Importance to Conditional Removability: Rethinking Visual Token Pruning in Multimodal Large Language Models
The paper argues that token importance alone is insufficient to determine safe removal of visual tokens in multimodal large language models, because removability depends on representation depth and the surrounding deletion set. Through controlled experiments, the authors show that the same tokens can have different effects when removed at different depths or contexts. They introduce CoRePrune, a training‑free two‑stage pruning framework that refreshes deletion effects as visual representations evolve and refines candidate tokens based on the current deletion set, achieving high performance retention across multiple backbones and reducing prefill time significantly.
arXiv Computer Vision
2d ago
Fewer Tokens, More Self-Teaching: On-Policy Self-Distillation for Extreme Visual Token Reduction
arXiv:2609.32353v2 Announce Type: replace Abstract: Visual token reduction is an effective way to accelerate multimodal large language models (MLLMs), but performance deteriorates rapidly under extre...
arXiv Machine Learning
Aug 11
LAVE: Latent Visual Evidence-Enhanced Planning for Video Tool-use Agents
arXiv:2608. 07585v1 Announce Type: cross Abstract: Long-video understanding requires models to efficiently acquire and reuse sparse visual evidence from long and redundant video streams.
arXiv Machine Learning
Jun 25
Semantic Allocation in Ordered Bottlenecks: Predictive Residual Inference for Visual Representation Learning
arXiv:2606. 25232v1 Announce Type: new Abstract: Ordered bottlenecks aim to provide utility at flexible budgets by assigning coarse information to early tokens and task-relevant detail to later ones.
arXiv AI
Aug 19
ScreenSearch: Uncertainty-Aware OS Exploration
ScreenSearch is a system for exploring desktop GUI states under partial observability. It combines structural screen retrieval, deduplication, and an ambiguity-aware PUCT graph-bandit to expand the reachable frontier while reducing state ambiguity. Across 11 applications, it collected over 1 M screenshots and 30 K deduplicated states, demonstrating that both ambiguity reduction and frontier exploration are essential for effective corpus building.
arXiv AI
Aug 26
VisCache: Visual KV Cache Pruning for Efficient Vision Large Language Model Inference
VisCache introduces a two-stage, plug‑and‑play framework for pruning visual key‑value caches in Vision Large Language Models without retraining. The first stage filters out temporally redundant keyframes, while the second stage, PruneKV, applies a parabolic layer‑wise budget and asymmetric update to selectively prune keys and fuse values, preserving essential context. Experiments show up to 2.35× speedup and significant memory savings with only 19–28% of the original cache retained, outperforming existing baselines.