Papers by Shyamnath Gollakota

5 papers
Reading Between the Lines: The One-Sided Conversation Problem (2026.findings-acl)

Copied to clipboard

Challenge: In many real-world scenarios, only one side of a conversation is available for processing.
Approach: They propose a one-sided conversation problem to reconstruct the missing speaker's turns and generate faithful summaries from one-side transcripts.
Outcome: The proposed model improves reconstructions with prompting, but smaller models require fine tuning.
LlamaPIE: Proactive In-Ear Conversation Assistants (2025.findings-acl)

Copied to clipboard

Challenge: LlamaPIE is the first real-time proactive assistant designed to enhance human conversations . it provides discreet, concise guidance delivered via hearable devices . traditional language models require explicit user invocation, but the assistant operates in the background .
Approach: They propose a two-model pipeline that decides when to respond and a larger model that generates the response.
Outcome: The proposed approach is effective in providing helpful, unobtrusive assistance on real-world datasets.
AV-Dialog: Spoken Dialogue Models with Audio-Visual Input (2026.acl-long)

Copied to clipboard

Challenge: AV-Dialog uses audio and visual cues to track the target speaker, predict turn-taking, and generate coherent responses.
Approach: They propose a multimodal dialog framework that uses both audio and visual cues to track the target speaker.
Outcome: AV-Dialog outperforms audio-only models under interference, reducing transcription errors, improving turn-taking prediction and human-rated dialogue quality.
Proactive Hearing Assistants that Isolate Egocentric Conversations (2025.emnlp-main)

Copied to clipboard

Challenge: Existing hearing assistants are "reactive" in that users manually prompt them to pick specific sound sources via spatial filtering or phone-based interfaces.
Approach: They propose a dual-model architecture that uses the wearer's self-speech as an anchor to infer conversational partners and suppress others.
Outcome: The proposed system can identify and separate conversation partners in multi-conversation settings without explicit user commands or prompts.
Beyond Turn-Based Interfaces: Synchronous LLMs as Full-Duplex Dialogue Agents (2024.emnlp-main)

Copied to clipboard

Challenge: Existing spoken dialogue models are half-duplex in nature and require explicit prompting by the user or implicit tracking of interruption or silence events.
Approach: They propose to integrate time information into Llama3-8b so that they run synchronously with the real-world clock.
Outcome: The proposed model outperforms state-of-the-art in dialogue meaningfulness while maintaining naturalness.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations