CfP | Real-Time Conversational Agents (RTCA) @ NeurIPS 2026

=F0=9F=8E=89 *Call for Papers and Demos*

*Real-Time Conversational Agents (RTCA): Toward Natural Multimodal
Interaction*

1st RTCA Workshop @ *NeurIPS 2026*, Sydney, Australia 11 or 12 December
2026

Website: https://rtcaneurips26.github.io/

We are pleased to share the Call for Papers and Demos for the inaugural
RTCA Workshop at NeurIPS 2026, focused on *real-time multimodal
conversational agents*: streaming speech, video, and language generation;
naturalness in interaction; and evaluation of live systems.

Conversational AI has moved from text chat into the real world, voice modes
that talk back, embodied avatars, agents that share our screens and tools.
To feel *natural*, these systems must operate in *real time*, streaming
while continuously listening, watching, and re-planning. This is
fundamentally harder than offline generation: latency, turn-taking,
backchannels, interruptions, and cross-modal alignment become first-class
problems that the offline paradigm sidesteps. Recent progress on
full-duplex speech=E2=80=93language models, real-time talking-head generati=
on, and
streaming ASR shows the regime is feasible, but the field still lacks
shared benchmarks, vocabulary, and methodology for *interactional*
 naturalness.

RTCA brings together researchers across speech, vision, language, HCI,
social-signal processing, and ML systems around three intertwined
questions: *real-time generation* under hard latency budgets, *naturalness
in interaction*, and *evaluation of live systems*.

=E2=9C=A8 *Topics of Interest*

We invite original contributions on topics including (but not limited to):

   - Streaming/low-latency speech synthesis, ASR, and full-duplex
   audio=E2=80=93language models
   - Real-time talking-head, avatar, and embodied video generation;
   lip-sync, gaze, expressivity under streaming
   - Streaming language models; incremental and speculative decoding for
   dialogue
   - Turn-taking, backchanneling, interruption handling, and floor
   management
   - Multimodal alignment under latency and partial-observation constraints
   - Prosody, emotion, and paralinguistic generation in interactive setting=
s
   - Memory, grounding, and tool use during live conversation
   - Evaluation of naturalness: perceptual studies, turn-taking metrics,
   perceived latency, interactive Turing-style tests
   - Datasets and benchmarks for *interactive* (not offline) evaluation
   - Efficient inference, on-device deployment, and the systems=E2=80=93qua=
lity
   trade-off
   - Safety, identity, and trust in real-time agents (deepfakes,
   persuasion, consent)

=F0=9F=93=9D *Submission Types*

We welcome:

   - *Full papers* (up to 8 pages) =E2=80=94 may be presented as posters an=
d/or
   contributed talks.
   - *Short papers* (up to 4 pages) =E2=80=94 work in progress or focused
   contributions.
   - *Demo papers* (Extended Abstracts or up to 2 pages)

All submissions must use the *NeurIPS 2026 style file* and be
formatted for *double-blind
review*. Page limits exclude references and appendices. Papers must be
submitted in *PDF format via OpenReview* (portal link to be published on
the workshop website).

The workshop is *non-archival*; authors retain the right to publish
elsewhere.

=F0=9F=93=85 *Important Dates* (End of day, Anywhere on Earth)

   - *Call for papers opens:* 18 July 2026
   - *Submission deadline* (papers and demos): *29 August 2026*
   - *Author notification:* 29 September 2026
   - *Workshop date:* 11 or 12 December 2026

=F0=9F=91=A5 *Organisers*

   - Niki Foteinopoulou =E2=80=94 Tavus, United Kingdom
   - Alessandro Conti =E2=80=94 Tavus, Italy
   - Jack Saunders =E2=80=94 Tavus, United Kingdom
   - Oya Celiktutan =E2=80=94 King's College London, United Kingdom
   - Cigdem Beyan =E2=80=94 University of Verona, Italy
   - Ioannis Patras =E2=80=94 Queen Mary University of London, United Kingd=
om

For more information, visit our website https://rtcaneurips26.github.io/ or
contact us at [email protected].

We look forward to your contributions!

    ----------------------------------------------------------------------------------------
    To unsubscribe from CHI-ANNOUNCEMENTS send an email to:
     mailto:[email protected]

    To manage your SIGCHI Mailing lists or read our polices see:
     https://sigchi.org/operations/listserv/
    ----------------------------------------------------------------------------------------