5 papers
The Crowded Embedding Space: A Mean-Field Mechanism for Emergent Marginalization in Retrieval-Augmented Agents
Shwan Ashrafi, Dan Roth
Retrieval-augmented generative agents rely on retrieval for grounding, yet are typically evaluated on a query-by-query basis. This isolates interactions that are geometrically coup…
Budget-Aware Anytime Reasoning with LLM-Synthesized Preference Data
Xuanming Zhang, Shwan Ashrafi, Aziza Mirsaidova +5
We study the reasoning behavior of large language models (LLMs) under limited computation budgets. In such settings, producing useful partial solutions quickly is often more practi…
Large-Scale Video Classification with Feature Space Augmentation coupled with Learned Label Relations and Ensembling
Choongyeun Cho, Benjamin Antin, Sanchit Arora +7
This paper presents the Axon AI's solution to the 2nd YouTube-8M Video Understanding Challenge, achieving the final global average precision (GAP) of 88.733% on the private test se…
Performance Analysis of CSMA with Multi-Packet Reception: The Inhomogeneous Case
Shwan Ashrafi, Chen Feng, Sumit Roy
The problem of Carrier Sense Multiple Access (CSMA) with multi-packet reception (MPR) is studied. Most prior work has focused on the homogeneous case, where all the mobile users ar…
On Dissemination Time of Random Linear Network Coding in Ad-hoc Networks
Shwan Ashrafi, Sumit Roy, Hamed Firooz
Random linear network coding (RLNC) unicast protocol is analyzed over a rapidly-changing network topology. We model the probability mass function (pmf) of the dissemination time as…