Showing papers from Applied Research Center, Tencent PCG Show all papers
Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
DeScore decouples chain-of-thought reasoning from scoring in video reward models to improve generalization and training stability. Its think-then-score design uses explicit reasoning followed by a dedicated regression head, optimized via cold-start and dual-objective reinforcement learning.
Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 2 on Hugging Face
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
AnchorWorld improves egocentric world simulation via full-body interaction supervision and anchor-view customization with consistent spatio-temporal dynamics.
Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 30 on Hugging Face
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
Edit-R2 uses reinforcement learning to reconstruct session intent and jointly optimize reasoning and generation for multi-turn image editing. It improves instruction following and consistency over accumulated constraints on the MICE-Bench benchmark.
Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
cIPO aligns text-to-video diffusion by deriving implicit preferences from reconstruction errors and concentrating optimization on high-error temporal segments to fix sparse artifacts.
Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
GARDO selectively regularizes high-uncertainty diffusion samples and adaptively updates reference models to prevent reward hacking while preserving diversity and sample efficiency.
Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 30 on Hugging Face · Code ★ 63
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
UniCustom fuses visual-semantic and appearance features before VLM encoding to eliminate cross-reference confusion in multi-reference image generation. Experiments show improved subject consistency, instruction following, and compositional fidelity over baselines.
Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.