Related papers: CrystalReasoner: Reasoning and RL for Property-Con…

Reinforcement learning (RL) has achieved notable performance in high-dimensional sequential decision-making tasks, yet remains limited by low sample efficiency, sensitivity to noise, and weak generalization under partial observability. Most…

We present MetaSpatial, the first reinforcement learning (RL)-based framework designed to enhance 3D spatial reasoning in vision-language models (VLMs), enabling real-time 3D scene generation without the need for hard-coded optimizations.…

Large Language Models (LLMs) with reasoning are trained to iteratively generate and refine their answers before finalizing them, which can help with applications to mathematics and code generation. We apply code generation with reasoning…

Crystal structure predictions based on the combination of first-principles calculations and machine learning have achieved significant success in materials science. However, most of these approaches are limited to predicting specific…

Reinforcement learning-based retrieval-augmented generation (RAG) methods enhance the reasoning abilities of large language models (LLMs). However, most rely only on final-answer rewards, overlooking intermediate reasoning quality. This…

Crystal generative models have shown rapid progress for accelerating the discovery of bulk, periodic materials. However, many material systems such as 2D superconductors, thin film semiconductors, and catalytic surfaces are diperiodic,…

The proliferation of online news poses a challenge to extracting structured timelines from unstructured content. While recent studies have shown that Large Language Models (LLMs) can assist Timeline Summarization (TLS), these approaches…

The role of reasoning in Audio Large Language Models remains widely underexplored, as introducing a reasoning process often degrades rather than improves performance during inference, a phenomenon we term test-time inverse scaling, where…

Generative models hold the promise of significantly expediting the materials design process when compared to traditional human-guided or rule-based methodologies. However, effectively generating high-quality periodic structures of materials…

The rapid evolution of Large Language Models (LLMs) has driven a growing demand for automated, high-performance system kernels to accelerate machine learning workloads. We introduce TritonRL, a domain-specialized 8B-scale LLM for Triton…

Vision-Language Models (VLMs) are advancing computational pathology with superior visual understanding capabilities. However, current systems often reduce diagnosis to directly output conclusions without verifiable evidence-linked…

Transformers trained via Reinforcement Learning (RL) with outcome-based supervision can spontaneously develop the ability to generate intermediate reasoning steps (Chain-of-Thought). Yet the mechanism by which sparse rewards drive policy…

Achieving both accuracy and diverse reasoning remains challenging for Large Language Models (LLMs) in complex domains like mathematics. A key bottleneck is evaluating intermediate reasoning steps to guide generation without costly human…

Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities across diverse tasks, yet they lag significantly behind humans in spatial reasoning. We investigate this gap through Transformation-Driven Visual Reasoning…

In recent years, the realm of crystalline materials has witnessed a surge in the development of generative models, predominantly aimed at the inverse design of crystals with tailored physical properties. However, spatial symmetry, which…

Large vision-language models (LVLMs) have witnessed significant progress on visual understanding tasks. However, they often prioritize language knowledge over image information on visual reasoning tasks, incurring performance degradation.…

While Large Language Models (LLMs) excel in certain reasoning tasks, they struggle in multi-agent games where the final outcome depends on the joint strategies of all agents. In multi-agent games, the non-stationarity of other agents brings…

Retrieval-Augmented Generation (RAG) mitigates hallucination in large language models (LLMs) by incorporating external knowledge during generation. However, the effectiveness of RAG depends not only on the design of the retriever and the…

The physical world is not merely visual; it is governed by rigorous structural and procedural constraints. Yet, the evaluation of vision-language models (VLMs) remains heavily skewed toward perceptual realism, prioritizing the generation of…

Retrieval-Augmented Generation (RAG) augments Large Language Models (LLMs) with external knowledge to improve factuality. However, existing RAG systems frequently underutilize the retrieved documents, failing to extract and integrate the…