8 citations · 24 across the 16 of their papers we have counts for
20 papers
Towards Better Exploration in Sequential Test-Time Scaling
Joseph Rance, Fabio Pizzati, Juil Sock +4
Test-time scaling improves language model reasoning by spending additional compute at inference. However, both classes of existing methods often fail to continue improving over lon…
GEOPHYS: The Geometry of Physical Plausibility
Christian Internò, Alexander Pondaven, Habon Issa +8
While humans can identify physically implausible events within milliseconds, machine learning approaches addressing the same problem are extremely slow and expensive. They either r…
LongCoT: Benchmarking Long-Horizon Chain-of-Thought Reasoning
Sumeet Ramesh Motwani, Daniel Nichols, Charles London +17
As language models are increasingly deployed for complex autonomous tasks, their ability to reason accurately over longer horizons becomes critical. An essential component of this…
ActionParty: Multi-Subject Action Binding in Generative Video Games
Alexander Pondaven, Ziyi Wu, Igor Gilitschenski +4
Recent advances in video diffusion have enabled the development of "world models" capable of simulating interactive environments. However, these models are largely restricted to si…
BLAZER: Bootstrapping LLM-based Manipulation Agents with Zero-Shot Data Generation
Rocktim Jyoti Das, Harsh Singh, Diana Turmakhan +5
Scaling data and models has played a pivotal role in the remarkable progress of computer vision and language. Inspired by these domains, recent efforts in robotics have similarly f…
LikePhys: Evaluating Intuitive Physics Understanding in Video Diffusion Models via Likelihood Preference
Jianhao Yuan, Fabio Pizzati, Francesco Pinto +5
Intuitive physics understanding in video diffusion models plays an essential role in building general-purpose physically plausible world simulators, yet accurately evaluating such…
Learning to Generate Rigid Body Interactions with Video Diffusion Models
David Romero, Ariana Bermudez, Viacheslav Iablochnikov +3
Recent video generation models have achieved remarkable progress and are now deployed in film, social media production, and advertising. Beyond their creative potential, such model…
Towards Reliable Identification of Diffusion-based Image Manipulations
Alex Costanzino, Woody Bayliss, Juil Sock +5
Changing facial expressions, gestures, or background details may dramatically alter the meaning conveyed by an image. Notably, recent advances in diffusion models greatly improve t…
PSyDUCK: Training-Free Steganography for Latent Diffusion
Aqib Mahfuz, Georgia Channing, Mark van der Wilk +3
Recent advances in generative AI have opened promising avenues for steganography, which can securely protect sensitive information for individuals operating in hostile environments…
AlignGuard: Scalable Safety Alignment for Text-to-Image Generation
Runtao Liu, I Chieh Chen, Jindong Gu +6
Text-to-image (T2I) models are widespread, but their limited safety guardrails expose end users to harmful content and potentially allow for model misuse. Current safety measures a…
Video Motion Transfer with Diffusion Transformers
Alexander Pondaven, Aliaksandr Siarohin, Sergey Tulyakov +2
We propose DiTFlow, a method for transferring the motion of a reference video to a newly synthesized one, designed specifically for Diffusion Transformers (DiT). We first process t…
MALT: Improving Reasoning with Multi-Agent LLM Training
Sumeet Ramesh Motwani, Chandler Smith, Rocktim Jyoti Das +6
Large Language Models (LLMs) often produce answers with a single chain-of-thought, which restricts their ability to explore reasoning paths or self-correct flawed outputs in comple…
MatchDiffusion: Training-free Generation of Match-cuts
Alejandro Pardo, Fabio Pizzati, Tong Zhang +4
Match-cuts are powerful cinematic tools that create seamless transitions between scenes, delivering strong visual and metaphorical connections. However, crafting match-cuts is a ch…
Specify and Edit: Overcoming Ambiguity in Text-Based Image Editing
Ekaterina Iakovleva, Fabio Pizzati, Philip Torr +1
Text-based editing diffusion models exhibit limited performance when the user's input instruction is ambiguous. To solve this problem, we propose (SANE)…
Model Merging and Safety Alignment: One Bad Model Spoils the Bunch
Hasan Abed Al Kader Hammoud, Umberto Michieli, Fabio Pizzati +4
Merging Large Language Models (LLMs) is a cost-effective technique for combining multiple expert LLMs into a single versatile model, retaining the expertise of the original ones. H…
Risks and Opportunities of Open-Source Generative AI
Francisco Eiras, Aleksandar Petrov, Bertie Vidgen +22
Applications of Generative AI (Gen AI) are expected to revolutionize a number of different areas, ranging from science & medicine to education. The potential for these seismic chan…
Near to Mid-term Risks and Opportunities of Open-Source Generative AI
Francisco Eiras, Aleksandar Petrov, Bertie Vidgen +21
In the next few years, applications of Generative AI are expected to revolutionize a number of different areas, ranging from science & medicine to education. The potential for thes…
Latent Guard: a Safety Framework for Text-to-image Generation
Runtao Liu, Ashkan Khakzar, Jindong Gu +3
With the ability to generate high-quality images, text-to-image (T2I) models can be exploited for creating inappropriate content. To prevent misuse, existing safety measures are ei…
On Pretraining Data Diversity for Self-Supervised Learning
Hasan Abed Al Kader Hammoud, Tuhin Das, Fabio Pizzati +3
We explore the impact of training with more diverse datasets, characterized by the number of unique samples, on the performance of self-supervised learning (SSL) under a fixed comp…
SynthCLIP: Are We Ready for a Fully Synthetic CLIP Training?
Hasan Abed Al Kader Hammoud, Hani Itani, Fabio Pizzati +3
We present SynthCLIP, a CLIP model trained on entirely synthetic text-image pairs. Leveraging recent text-to-image (TTI) networks and large language models (LLM), we generate synth…