8 papers
Hard or Just Unreached? Diagnosing the Sampling Blind Spot in Math-Reasoning Difficulty Estimation
Luca Zhou, Sajel Shah, Emanuele Rodolà +1
Math and science reasoning benchmarks rely on pass@k, the fraction of sampled chains that reach gold, as the canonical per-example difficulty signal. The same signal drives RL with…
Steering Vectors are an Adversarial Attack Surface
Abzal Aidakhmetov, Donato Crisostomi, Tommaso Mencattini +3
Activation steering has become a popular way to control Large Language Model (LLM) behavior without fine-tuning. Since the technique is plug-and-play, users share datasets and prec…
How Neural Losses Shape VAE Latents
Giorgio Strano, Luca Cerovaz, Michele Mancusi +2
Modern VAEs are rarely trained with the pointwise likelihood implied by the standard -VAE objective. In practice, pointwise reconstruction is often combined with perceptual and…
Communicating Sound Through Natural Language
Emanuele Rossi, Emanuele RodolÃ
Natural language is widely used to describe, prompt, and control audio systems, but rarely serves as the representation carrying audio itself. We introduce lexical acoustic coding…
Zero-Shot Quantization via Weight-Space Arithmetic
Daniele Solombrino, Antonio Andrea Gargiulo, Alessandro Zirilli +3
We show that robustness to post-training quantization (PTQ) is a transferable direction in weight space. We call this direction the quantization vector: extracted from a donor task…
Multi-objective Evolutionary Merging Enables Efficient Reasoning Models
Mario Iacobelli, Adrian Robert Minut, Tommaso Mencattini +5
Reasoning models achieve strong performance on complex problems by leveraging long chains of thought, but this deliberate reasoning incurs substantial inference-time cost. The Long…