arXiv subjects

Erez Koifman

Publications and source records attributed to Erez Koifman.

3 recordsLinked to original sources

arXiv2026

Sensor to Pixels: Decentralized Swarm Gathering via Image-Based Reinforcement Learning

This study highlights the potential of image-based reinforcement learning methods for addressing swarm-related tasks. In multi-agent reinforcement learning, effective policy learning depends on how agents sense, interpret, and process inputs. Traditional approaches often rely on handcrafted feature extraction or raw vector-based representations, which limit the scalability and efficiency of learned policies concerning input order and size. In this work we propose an image-based reinforcement learning method for decentralized control of a multi-agent system, where observations are encoded as structured visual inputs that can be processed by Neural Networks, extracting its spatial features and producing novel decentralized motion control rules. We evaluate our approach on a multi-agent convergence task of agents with limited-range and bearing-only sensing that aim to keep the swarm cohesive during the aggregation. The algorithm's performance is evaluated against two benchmarks: an analytical solution proposed by Bellaiche and Bruckstein, which ensures convergence but progresses slowly, and VariAntNet, a neural network-based framework that converges much faster but shows medium success rates in hard constellations. Our method achieves high convergence, with a pace nearly matching that of VariAntNet. In some scenarios, it serves as the only practical alternative.

cs.LG↗

arXiv2025

WAVECLIP: Wavelet Tokenization for Adaptive-Resolution CLIP

We introduce WAVECLIP, a single unified model for adaptive resolution inference in CLIP, enabled by wavelet-based tokenization. WAVECLIP replaces standard patch embeddings with a multi-level wavelet decomposition, enabling the model to process images coarse to fine while naturally supporting multiple resolutions within the same model. At inference time, the model begins with low resolution tokens and refines only when needed, using key-value caching and causal cross-level attention to reuse computation, effectively introducing to the model only new information when needed. We evaluate WAVECLIP in zero-shot classification, demonstrating that a simple confidence-based gating mechanism enables adaptive early exits. This allows users to dynamically choose a compute-accuracy trade-off using a single deployed model. Our approach requires only lightweight distillation from a frozen CLIP teacher and achieves competitive accuracy with significant computational savings.

cs.CV↗

arXiv2025

VariAntNet: Learning Decentralized Control of Multi-Agent Systems

A simple multi-agent system can be effectively utilized in disaster response applications, such as firefighting. Such a swarm is required to operate in complex environments with limited local sensing and no reliable inter-agent communication or centralized control. These simple robotic agents, also known as Ant Robots, are defined as anonymous agents that possess limited sensing capabilities, lack a shared coordinate system, and do not communicate explicitly with one another. A key challenge for simple swarms lies in maintaining cohesion and avoiding fragmentation despite limited-range sensing. Recent advances in machine learning offer effective solutions to some of the classical decentralized control challenges. We propose VariAntNet, a deep learning-based decentralized control model designed to facilitate agent swarming and collaborative task execution. VariAntNet includes geometric features extraction from unordered, variable-sized local observations. It incorporates a neural network architecture trained with a novel, differentiable, multi-objective, mathematically justified loss function that promotes swarm cohesiveness by utilizing the properties of the visibility graph Laplacian matrix. VariAntNet is demonstrated on the fundamental multi-agent gathering task, where agents with bearing-only and limited-range sensing must gather at some location. VariAntNet significantly outperforms an existing analytical solution, achieving more than double the convergence rate while maintaining high swarm connectivity across varying swarm sizes. While the analytical solution guarantees cohesion, it is often too slow in practice. In time-critical scenarios, such as emergency response operations where lives are at risk, slower analytical methods are impractical and justify the loss of some agents within the swarm. This paper presents and analyzes this trade-off in detail.

cs.LG↗