12 papers
Thinking into the Future: Latent Lookahead Training for Transformers
Lorenzo Noci, Gregor Bachmann, Seyed-Mohsen Moosavi-Dezfooli +1
Autoregressive language models trained with next-token prediction generate text by sampling one discrete token at a time. Although very scalable, this objective forces the model to…
The Potential of CoT for Reasoning: A Closer Look at Trace Dynamics
Gregor Bachmann, Yichen Jiang, Seyed Mohsen Moosavi Dezfooli +1
Chain-of-thought (CoT) prompting is a de-facto standard technique to elicit reasoning-like responses from large language models (LLMs), allowing them to spell out individual steps…
AstroMMBench: A Benchmark for Evaluating Multimodal Large Language Models Capabilities in Astronomy
Jinghang Shi, Xiaoyu Tang, Yang Huang +4
Astronomical image interpretation presents a significant challenge for applying multimodal large language models (MLLMs) to specialized scientific tasks. Existing benchmarks focus…
Learning Private Representations through Entropy-based Adversarial Training
Tassilo Klein, Moin Nabi
How can we learn a representation with high predictive power while preserving user privacy? We present an adversarial representation learning method for sanitizing sensitive conten…
Chain-of-Sketch: Enabling Global Visual Reasoning
Aryo Lotfi, Enrico Fini, Samy Bengio +2
Modern vision models have achieved remarkable success in benchmarks where local features provide critical information about the target. There is now a growing interest in tackling…
Contrastive Perplexity for Controlled Generation: An Application in Detoxifying Large Language Models
Tassilo Klein, Moin Nabi
The generation of toxic content by large language models (LLMs) remains a critical challenge for the safe deployment of language technology. We propose a novel framework for implic…