1 citations · 1 across the 10 of their papers we have counts for
6 papers · 1 filter
IHBench: Evaluating Post-Interruption Recovery in Voice Agents with Structured Workflows
Ahmad Salimi, Wentao Ma, Yuzhi Tang +3
Voice agents deployed in structured workflows (customer service, healthcare scheduling, account management) must handle frequent user interruptions while maintaining progress throu…
Let the Batch Decide, On- or Off-Policy: Effective Sample Size for RL Post-Training
Rasool Fakoor, Murdock Aubry, Nicholas Stranges +1
Reinforcement learning (RL) is structurally harder than supervised learning because the policy changes the data distribution it learns from. The resulting fragility is especially v…
ProactBench: Beyond What The User Asked For
Sepehr Harfi, Ahmad Salimi, Dongming Shen +1
Most LLM benchmarks score how well a model responds to explicit requests. They leave unmeasured a different conversational ability: noticing and acting on needs the user has implie…
The Pokémon Theorem and other Fairness Impossibility Results
Daniel Matsui Smola, Alex Smola
Fairness impossibility results often look like distinct scalar incompatibility statements. We show that several share one RKHS geometry: fairness criteria are linear constraints on…
EmergentTTS-Eval: Evaluating TTS Models on Complex Prosodic, Expressiveness, and Linguistic Challenges Using Model-as-a-Judge
Ruskin Raj Manku, Yuzhi Tang, Xingjian Shi +2
Text-to-Speech (TTS) benchmarks often fail to capture how well models handle nuanced and semantically complex text. Building on , we introduce $\textit{Emerge…
L3Ms -- Lagrange Large Language Models
Guneet S. Dhillon, Xingjian Shi, Yee Whye Teh +1
Supervised fine-tuning (SFT) and alignment of large language models (LLMs) are key steps in providing a good user experience. However, the concept of an appropriate alignment is in…