Related papers: Knowing When to Answer: Adaptive Confidence Refine…
Most domain adaptation methods for machine reading comprehension (MRC) use a pre-trained question-answer (QA) construction model to generate pseudo QA pairs for MRC transfer. Such a process will inevitably introduce mismatched pairs (i.e.,…
High-precision control tasks present substantial challenges for reinforcement learning (RL) algorithms, frequently resulting in suboptimal performance attributed to network approximation inaccuracies and inadequate sample quality.These…
Quantization is a fundamental optimization for many machine-learning use cases, including compressing gradients, model weights and activations, and datasets. The most accurate form of quantization is \emph{adaptive}, where the error is…
Artificial neural network training with stochastic gradient descent can be destabilized by "bad batches" with high losses. This is often problematic for training with small batch sizes, high order loss functions or unstably high learning…
End-to-end approaches for automatic speech recognition (ASR) benefit from directly modeling the probability of the word sequence given the input audio stream in a single neural network. However, compared to conventional ASR systems, these…
Audio-visual quality assessment (AVQA) is essential for streaming, teleconferencing, and immersive media. In realistic streaming scenarios, distortions are often asymmetric, where one modality may be severely degraded while the other…
Humans are capable of processing speech by making use of multiple sensory modalities. For example, the environment where a conversation takes place generally provides semantic and/or acoustic context that helps us to resolve ambiguities or…
Advances in voice conversion and text-to-speech synthesis have made automatic speaker verification (ASV) systems more susceptible to spoofing attacks. This work explores modest refinements to the AASIST anti-spoofing architecture. It…
Aiming at answering questions based on the content of remotely sensed images, visual question answering for remote sensing data (RSVQA) has attracted much attention nowadays. However, previous works in RSVQA have focused little on the…
In this study, we try to address the problem of leveraging visual signals to improve Automatic Speech Recognition (ASR), also known as visual context-aware ASR (VC-ASR). We explore novel VC-ASR approaches to leverage video and text…
Modern end-to-end automatic speech recognition (ASR) models like Whisper not only suffer from reduced recognition accuracy in noise, but also exhibit overconfidence - assigning high confidence to wrong predictions. We conduct a systematic…
Language model outputs are not always reliable, thus prompting research into how to adapt model responses based on uncertainty. Common approaches include: \emph{abstention}, where models refrain from generating responses when uncertain; and…
Facebook AI Research introduced KRISP [4], which integrates structured external knowledge into pipelines for vision-language reasoning. Despite its effectiveness, the original model has been developed for industrial-scale training, is…
Reinforcement learning post-training has substantially improved the reasoning accuracy of vision-language models, yet the resulting policies remain poorly calibrated. Terminal correctness rewards provide no gradient that penalizes confident…
Audio-visual question answering (AVQA) requires reference to video content and auditory information, followed by correlating the question to predict the most precise answer. Although mining deeper layers of audio-visual information to…
We present ACAR (Adaptive Complexity and Attribution Routing), a measurement framework for studying multi-model orchestration under auditable conditions. ACAR uses self-consistency variance (sigma) computed from N=3 probe samples to route…
Ensuring safety in Reinforcement Learning (RL), typically framed as a Constrained Markov Decision Process (CMDP), is crucial for real-world exploration applications. Current approaches in handling CMDP struggle to balance optimality and…
Audio deepfake detection has become increasingly challenging due to rapid advances in speech synthesis and voice conversion technologies, particularly under channel distortions, replay attacks, and real-world recording conditions. This…
Acoustic foundation models, fine-tuned for Automatic Speech Recognition (ASR), suffer from performance degradation in wild acoustic test settings when deployed in real-world scenarios. Stabilizing online Test-Time Adaptation (TTA) under…
Solving chance-constrained optimal control problems for systems subject to non-stationary uncertainties is a significant challenge.Conventional robust model predictive control (MPC) often yields excessive conservatism by relying on static…