Hugging Face Trending Papers July 7, 2026

Progressive Reasoning with Primitive Correction for Compositional Zero-Shot Learning

Read the original on Hugging Face Trending Papers →

Compositional Zero-Shot Learning (CZSL) aims to combine known attributes and objects as primitives for recognizing previously unseen attribute-object pairs. Prior works either predict attributes and objects independently, missing their strong contextual dependency, or use unidirectional conditional modeling (e.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv AI

1d ago

Zero-Shot Instruction Following in RL via Structured LTL Representations

arXiv:2602. 14344v2 Announce Type: replace-cross Abstract: We study instruction following in multi-task reinforcement learning, where an agent must zero-shot execute novel tasks not seen during training.

By Mathias Jackermeier, Mattia Giuri, Jacques Cloete, Alessandro Abate

agents reinforcement-learning

arXiv AI

Jul 1

Thinking Before Retrieving: Robust Zero-Shot Composed Image Retrieval via Strategic Planning and Self-Criticism

arXiv:2606. 31222v1 Announce Type: new Abstract: Composed image retrieval requires identifying a target image from a gallery by integrating a reference image with a textual modification instruction.

By Gunho Jung, Jeong-Woo Park, Seon Bin Kim, Seong-Whan Lee

rag

arXiv AI

Jun 4

Belief-Aware VLM Model for Human-like Reasoning

arXiv:2604. 09686v2 Announce Type: replace Abstract: Traditional neural network models for intent inference rely heavily on observable states and struggle to generalize across diverse tasks and dynamic environments.

By Anshul Nayak, Shahil Shaik, Yue Wang

llms diffusion reinforcement-learning multimodal

arXiv AI

Jul 2

Learning to Compose: Revisiting Proxy Task Design for Zero-Shot Composed Image Retrieval

arXiv:2607. 00374v1 Announce Type: cross Abstract: Composed Image Retrieval (CIR) retrieves a target image from a reference image and a textual modification.

By Jingjing Zhang, Lei Zhang, Zheren Fu, Zhendong Mao

multimodal benchmarks

arXiv AI

Jun 11

ProcessThinker: Enhancing Multi-modal Large Language Models Reasoning via Rollout-based Process Reward

arXiv:2606. 11209v1 Announce Type: cross Abstract: Visual question answering increasingly requires multi-step reasoning.

By Jingpei Wu, Xiao Han, Weixiang Shen, Boer Zhang, Zifeng Ding, Volker Tresp

llms nlp reinforcement-learning fine-tuning multimodal benchmarks

arXiv AI

Jun 2

From Demonstrations to Rewards: Test-Time Prompt Optimization for VLM Reward Models

arXiv:2606. 00083v1 Announce Type: cross Abstract: Reinforcement learning relies on accurate reward functions, which are often hand-crafted or even unavailable in real-world applications, such as robotics.

By Christian Gumbsch, Leonardo Barcellona, Lennard Sch\"unemann, Platon Karageorgis, Andrii Zadaianchuk, Zehao Wang, Sergey Zakharov, Fabien Despinoy, Rahaf Aljundi, Efstratios Gavves

llms reinforcement-learning robotics multimodal

Related stories

Zero-Shot Instruction Following in RL via Structured LTL Representations

Thinking Before Retrieving: Robust Zero-Shot Composed Image Retrieval via Strategic Planning and Self-Criticism

Belief-Aware VLM Model for Human-like Reasoning

Learning to Compose: Revisiting Proxy Task Design for Zero-Shot Composed Image Retrieval

ProcessThinker: Enhancing Multi-modal Large Language Models Reasoning via Rollout-based Process Reward

From Demonstrations to Rewards: Test-Time Prompt Optimization for VLM Reward Models