Related papers: Seg-Zero: Reasoning-Chain Guided Segmentation via …

Composed Image Retrieval (CIR) aims to retrieve target images that closely resemble a reference image while integrating user-specified textual modifications, thereby capturing user intent more precisely. Existing training-free zero-shot CIR…

Most reward models for visual generation reduce rich human judgments to a single unexplained score, discarding the reasoning that underlies preference. We show that teaching reward models to produce explicit, multi-dimensional critiques…

Reverse Chain-of-Thought Generation (RCG) synthesizes reasoning traces from query-answer pairs, but runs the risk of producing post-hoc rationalizations: when models can see the answer during generation, the answer serves as a cognitive…

Building a semantic parser quickly in a new domain is a fundamental challenge for conversational interfaces, as current semantic parsers require expensive supervision and lack the ability to generalize to new domains. In this paper, we…

This work addresses a fundamental barrier in recommender systems: the inability to generalize across domains without extensive retraining. Traditional ID-based approaches fail entirely in cold-start and cross-domain scenarios where new…

Zero-shot learning strives to classify unseen categories for which no data is available during training. In the generalized variant, the test samples can further belong to seen or unseen categories. The state-of-the-art relies on Generative…

Visual concept discovery has long been deemed important to improve interpretability of neural networks, because a bank of semantically meaningful concepts would provide us with a starting point for building machine learning models that…

Unified Multimodal Models (UMMs) excel in general tasks but struggle to bridge the gap between personalized understanding and generation. Prior works largely rely on implicit token-level alignment via supervised fine-tuning, which fails to…

Recent advances in generative video models are increasingly driven by post-training and test-time scaling, both of which critically depend on the quality of video reward models (RMs). An ideal reward model should predict accurate rewards…

Large language models (LLMs) achieve strong performance by generating long chains of thought, but longer traces always introduce redundant or ineffective reasoning steps. One typical behavior is that they often perform unnecessary…

Diffusion-based large language models offer a non-autoregressive alternative for text generation, but enabling them to perform complex reasoning remains challenging. Reinforcement learning has recently emerged as an effective post-training…

Mathematical reasoning is a key benchmark for large language models. Reinforcement learning is a standard post-training mechanism for improving the reasoning capabilities of large language models, yet performance remains sensitive to the…

A serious issue that harms the performance of zero-shot visual recognition is named objective misalignment, i.e., the learning objective prioritizes improving the recognition accuracy of seen classes rather than unseen classes, while the…

Future advancements in robot autonomy and sophistication of robotics tasks rest on robust, efficient, and task-dependent semantic understanding of the environment. Semantic segmentation is the problem of simultaneous segmentation and…

Remote sensing has become critical for understanding environmental dynamics, urban planning, and disaster management. However, traditional remote sensing workflows often rely on explicit segmentation or detection methods, which struggle to…

Reasoning ability is crucial for solving challenging tasks. With the advancement of foundation models, such as the emergence of large language models (LLMs), a wide range of reasoning strategies has been proposed, including test-time…

Semantic segmentation models are limited in their ability to scale to large numbers of object classes. In this paper, we introduce the new task of zero-shot semantic segmentation: learning pixel-wise classifiers for never-seen object…

This study investigates the spatial reasoning capabilities of vision-language models (VLMs) through Chain-of-Thought (CoT) prompting and reinforcement learning. We begin by evaluating the impact of different prompting strategies and find…

We present SegLLM, a novel multi-round interactive reasoning segmentation model that enhances LLM-based segmentation by exploiting conversational memory of both visual and textual outputs. By leveraging a mask-aware multimodal LLM, SegLLM…

Generalized Zero-shot Semantic Segmentation aims to segment both seen and unseen categories only under the supervision of the seen ones. To tackle this, existing methods adopt the large-scale Vision Language Models (VLMs) which obtain…