Speech-LLMs are expensive to run, making compression important for real-world deployment. However, compressed models are usually selected using aggregate word error rate (WER), which can hide how pruning affects different demographic groups. In this work, we systematically study the effect of audio encoder pruning on S...
Ganesh Pavan Kartikeya Bharadwaj Kolluri, Michael Kampouridis, Ravi Shekhar· 0 citations
Turning decoder-only large language models (LLMs) into strong dense retrievers typically requires some form of retriever training. In this paper, we ask whether LLMs can instead be prompted to produce effective representations for dense retrieval given only a few in-context examples. To answer this, we introduce RICE (...
Nour Jedidi, Abdul Basit Ali, Hang Li et al.· 0 citations
LoLBench is a multilingual benchmark of 100 tasks across 29 software systems in five domains that shows that both perception and implementation remain central challenges for coding agents in practical modular development on large software systems.
Explicit prosodic cues may help automatic speech recognition (ASR) of spontaneous speech, but auxiliary representations typically require additional trainable components, making it unclear whether gains come from the auxiliary information or the fusion mechanism. We address this using a frozen HuBERT backbone and a 64-...
Ki Woong Moon, Dan Brenner· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
The vocal tract is the region of the human body responsible for filtering one's voice to create speech. In this paper, we present a differentiable and GPU accelerated acoustic simulator for the vocal tract. The differentiable simulator synthesizes speech by propagating sound along an acoustic tube model of the vocal tr...
Eric Ming Chen, Jin Woo Lee, Vincent Sitzmann· 0 citations
Tandem Token WaterMark (TTMARK), a general pairwise watermarking framework that extends distortion-free watermarking from individual tokens to adjacent token pairs, and introduces a branch-isolating concatenated tandem generation algorithm that efficiently constructs the joint distribution in a single forward pass.
Rui-Bo Chen, Zheng-Mian Hu, Dong-Hang Lu et al.· 0 citations
We investigate the extent to which the Hamas attacks on Israel of October 7, 2023, have affected German social media debates about Judaism and Israel. For this, we develop an approach to detect 26 anti-Semitic categories in user postings via large language models (LLMs). The approach is applied to Facebook and Telegram...
Three findings emerge: in the restless task, neural models trained without rewards predict held-out choices better than four simple training-fitted behavioral baselines, and at some reward weights, neural networks predict better than a pooled reinforcement-learning model but have less faithful changes in choice probabi...
Real-world embodied agents often pursue independent objectives within a shared physical environment, where their actions can alter the conditions faced by others. Existing benchmarks, however, typically assume shared goals or explicitly prescribed interaction protocols, leaving such emergent physical coupling underexpl...
Jie Yang, Jia-Jun Chen, Jia-Zheng Zhou et al.· 0 citations
Understanding how individual traits influence team performance is valuable, but these traits are not always directly observable. Prior research has inferred traits like trust from behavioral data. We analyze conversational data to identify team traits and their correlation with teaming outcomes. Using transcripts from...
Ali Jalal-Kamali, Nikolos Gurney, David Pynadath· 0 citations
Vision-language models (VLMs) may accept false visual premises, answering questions about a target object's color, count, location, or state even when it is absent. We call this reliability-critical behavior a target-absence grounding failure. Existing visual-grounding detectors primarily rely on generated responses, h...
In recent years, the performance of large language models (LLMs) on reasoning tasks has been remarkable, even surpassing human capabilities on various benchmarks. However, there remains a lack of clear understanding in the academic community regarding how the structure and internal parameters of LLMs progressively solv...
Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose. The post Flint-interactive: A language for creating interactive data visualizations appeared first on Microsoft Research.
