Related papers: Self-Evolving Spatial Reasoning in Vision Language…

Vision Language Models (VLMs) achieve strong performance on many vision-language tasks but often struggle with spatial reasoning$\unicode{x2014}$a prerequisite for many applications. Empirically, we find that a dataset produced by a current…

Vision-language models (VLMs) achieve strong performance on spatial reasoning benchmarks, yet it remains unclear whether this reflects structured 3D understanding or reliance on statistical shortcuts in natural images. We introduce a…

We introduce MERGE, a system for situational grounding of actors, objects, and events in dynamic human-robot group interactions. Effective collaboration in such settings requires consistent situational awareness, built on persistent…

Visual-Semantic Embedding (VSE) is a prevalent approach in image-text retrieval by learning a joint embedding space between the image and language modalities where semantic similarities would be preserved. The triplet loss with…

Vision-language models (VLMs) have advanced rapidly, yet they still struggle with basic spatial reasoning. Despite strong performance on general benchmarks, modern VLMs remain brittle at understanding 2D spatial relationships such as…

Spatial understanding is a critical capability for vision foundation models. While recent advances in large vision models or vision-language models (VLMs) have expanded recognition capabilities, most benchmarks emphasize localization…

Large Language Model (LLM)-guided evolutionary search is increasingly used for automated algorithm discovery, yet most current methods track search progress primarily through executable programs and scalar fitness. Even when…

Vision-language models (VLMs) adapted to the medical domain have shown strong performance on visual question answering benchmarks, yet their robustness against two critical failure modes, hallucination and sycophancy, remains poorly…

Visual grounding, localizing objects from natural language descriptions, represents a critical bridge between language and vision understanding. While multimodal large language models (MLLMs) achieve impressive scores on existing…

Evaluating the symbolic reasoning of large language models (LLMs) calls for geometry benchmarks that require multi-step proofs grounded in both text and diagrams. However, existing benchmarks are often limited in scale and rarely provide…

Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in vision-language answering tasks. Despite their strengths, these models often encounter challenges in achieving complex reasoning tasks such as…

Improving embodied reasoning in multimodal-large-language models (MLLMs) is essential for building vision-language-action models (VLAs) on top of them to readily translate multimodal understanding into low-level actions. Accordingly, recent…

Following the success of Group Relative Policy Optimization (GRPO) in foundation LLMs, an increasing number of works have sought to adapt GRPO to Visual Large Language Models (VLLMs) for visual perception tasks (e.g., detection and…

Image scoring is a crucial task in numerous real-world applications. To trust a model's judgment, understanding its rationale is essential. This paper proposes a novel training method for Vision Language Models (VLMs) to generate not only…

Understanding how language and embedding models encode semantic relationships is fundamental to model interpretability. While early word embeddings exhibited intuitive vector arithmetic (''king'' - ''man'' + ''woman'' = ''queen''), modern…

Learning open-vocabulary physical skills for simulated agents presents a significant challenge in artificial intelligence. Current reinforcement learning approaches face critical limitations: manually designed rewards lack scalability…

The evolution of Large Language Model (LLM) reasoning is bottlenecked by the scarcity of high-quality process data. While self-alignment via endogenous rewards offers a solution, mining valid supervision faces three challenges: (1) Label…

Long-term memory is becoming a central bottleneck for language agents. Exsting RAG and GraphRAG systems largely treat memory graphs as static retrieval middleware, which limits their ability to recover complete evidence chains from partial…

Large Vision-Language Models (LVLMs) have become powerful general-purpose assistants, yet their predictions often lack reliability and interpretability due to insufficient grounding in visual evidence. The emerging thinking-with-images…

Spatial reasoning, which requires ability to perceive and manipulate spatial relationships in the 3D world, is a fundamental aspect of human intelligence, yet remains a persistent challenge for Multimodal large language models (MLLMs).…