Latest papers
I have greatly enjoyed spending many years in studying parallel computing. My journey goes thorough MP-C, PLURAL, Async Plural, HAL, RC64 and more. As a PhD student at Princeton I studied a combination of shared memory and message passing,…
With the emergence of large-scale image-text pre-training models, e.g., CLIP, text-video retrieval has experienced substantial advances in recent years. Existing best-performing methods involve aligning cross-modal semantics at individual,…
As photons propagate through curved spacetime, gravitational effects become unavoidable. In particular, gravitational redshift can induce significant distortion in photon wave packets, making it es?sential to investigate parameter…
We present an extension of Triangolazioni (a Cultural Heritage webapp) to enrich curated content with context-dependent, external information provided by Large Language Models (LLMs) within a loosely-coupled architecture agnostic to the…
Recent image-generation models and multimodal agents can produce high-quality visuals for increasingly complex visual communication tasks. Yet their raster outputs remain difficult to use directly because meaningful content and…
Contact-rich manipulation remains challenging because successful control depends on physical interaction cues that are often weakly observable from vision alone. Recent tactile world action models jointly model future visual observations…
The divergence of Feynman graph integrals is one of the central issues in the study of perturbative quantum field theories. A rigorous formulation of these integrals usually requires renormalization. In this paper, we prove that the Feynman…
Natural-language descriptions have become a flexible interface for controlling generated speech. Existing evaluations largely assess whether an output matches a prompt, but prompt matching alone does not reveal whether characteristics…
Identifying the ``Inflamed'' immunophenotype in Gastric Adenocarcinoma predicts immunotherapy response but requires an expensive 10-gene RNA signature. While deep learning on standard H\&E slides offers a scalable alternative, conventional…
Although semantic watermarking is considered a promising safeguard for images generated by Latent Diffusion Models (LDMs), the reliance of the watermark detection pipeline on neural networks introduces a critical yet underexplored backdoor…
Graphs model relational data throughout science and industry, from citation networks to product co-purchase graphs. Because the nodes of many such graphs carry rich text, a growing line of work applies large language models (LLMs) to graph…
Digital forensics has become an integral part of modern criminal proceedings, yet its effective integration remains challenging because of increasing data volumes, evolving technologies, and complex interactions between technical and legal…
Tool-integrated vision-language agents have made remarkable progress on compositional and multi-step visual reasoning. Yet their outputs frequently exhibit unfaithfulness: the stated reasoning path diverges from the computation that…
DNA molecules are so small that it might be practical to use their frequency vectors to encode messages. More precisely, a sender can inject $M_X$ copies of the string $X =$ CATCATCAT into a pool and the receiver can recover $M_X$ by…
Recent advancements of zero-shot Named Entity Recognition (NER) establish strong baselines by formulating sequence labeling into question answering where Large Language Models (LLMs) can be naturally adopted. However, existing LLM-based…
Latent Flow Models have revolutionized compressed-space image synthesis, yet their application to high-fidelity inverse problems remains bottlenecked. In this paper, we trace this dilemma to a fundamental geometric limitation of pre-trained…
Reinforcement learning (RL) for document parsing often relies on reference-based rewards rooted in edit distance (e.g., tree edit distance), yet it remains hard to optimize in the high-accuracy regime because such rewards become weakly…
Bruhat decompositions give cellular models for split algebraic groups, flag varieties, and maximal compact groups, but motivic boundaries retain orientation and torus-translation data lost in the flag quotient. Over a perfect field of…
The Mahabharata and the Ramayana constitute the two major Sanskrit epics of ancient India. Previous network analysis revealed substantial structural similarities between their character networks, alongside differences consistent with their…
Large Language Models have achieved substantial progress in reasoning capabilities. Yet in low-resource native settings, many suffer from cross-lingual collapse, reverting to English during intermediate steps that require complex logical…