Showing papers from Kuaishou- 快手科技 Show all papers
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.
Sydney Poster Session 3, Wed, Dec 9, 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.
Sydney Poster Session 3, Wed, Dec 9, 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.
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.
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.
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.
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.
Paris Poster Session 4, Thu, Dec 10, 5:30 PM–7:30 PM, Paris Poster Hall · 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.
SpatialFlow-GRPO introduces region-aware rewards to replace whole-image feedback, improving fine-grained image editing via spatially aligned policy updates.
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.
ViDiC introduces a video difference captioning task and ViDiC-1K benchmark that reveals large multimodal models struggle with fine-grained comparative video perception.
Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 29 on Hugging Face · Code ★ 15
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.
CaC advances video reward models via hierarchical spatiotemporal concentrating, improving fine-grained anomaly accuracy by 25.7% and reducing generated-video anomalies by 11.7%.
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.
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.
DELTAVID improves video MLLM fine-grained spatiotemporal perception by training cross-video difference spotting, boosting performance across multiple video understanding benchmarks.
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.
UxSID captures target-aware preferences via semantic-group shared interest memory and dual-level attention, achieving state-of-the-art results and 0.337% revenue lift.
Sydney Poster Session 5, Thu, Dec 10, 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.
Archer applies entropy-aware dual-token constraints to RLVR, modulating optimization strengths across reasoning and knowledge tokens to improve mathematical and code performance.
Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 21 on Hugging Face · Code ★ 44
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.
TMPO replaces scalar reward maximization with trajectory-level reward distribution matching via Softmax Trajectory Balance, improving diffusion alignment diversity by 9.1% while avoiding reward hacking and mode collapse.
Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 3 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.
ARGUS introduces multi-view identity mosaic injection and counterfactual training to preserve subject identity across motion, viewpoint changes, and occlusions in video generation.
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.
OneSearch-V2 uses thought-augmented query understanding and reasoning self-distillation to improve generative search, boosting item CTR by 3.98% without added latency.
Paris Poster Session 2, Wed, Dec 9, 5:00 PM–7:00 PM, Paris Poster Hall · Published 2026 · Code ★ 174
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.
Bian Que is an agentic framework that arranges flexible skills for online system operations, reducing alerts by 75% and cutting resolution time by over 50%.
Paris Poster Session 1, Wed, Dec 9, 12:30 PM–2:30 PM, Paris Poster Hall · 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.
TIGER-FG uses text-guided implicit fine-grained grounding and dual distillation to improve cropped-query e-commerce retrieval, boosting Recall@1 by up to 34.4 points without object detection.
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.
Leverage Score Sampling enables scalable data diversification for LM pretraining via leverage scores, improving diversity by 9.2% and speed by 72×.
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.
LatentOmni replaces text chain-of-thought with interleaved audio-visual latent reasoning states to preserve dense sensory signals, improving joint reasoning over explicit text baselines.
Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 44 on Hugging Face · Code ★ 24
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.
GISA introduces 373 human-crafted information-seeking queries with structured answers, live updates, and search trajectories to benchmark autonomous search agents, revealing state-of-the-art models achieve under 20% accuracy.
Paris Poster Session 1, Wed, Dec 9, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026 · ▲ 26 on Hugging Face · Code ★ 37
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.
RLVR training causes reasoning outputs to structurally converge on seen prompts, and Min-kNN Distance detects this collapse via black-box sampling to identify contamination.
Paris Poster Session 6, Fri, Dec 11, 2:30 PM–4:30 PM, Paris Poster Hall · Published 2026 · ▲ 2 on Hugging Face · Code ★ 8
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.
Manifold drift pushes flow preference optimization off the data manifold via terminal displacement normal components; ThermoDPO-weighted improves strict score and image metrics over FlowDPO.
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.
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.