Three papers have been accepted to NeurIPS2026
For the NeurIPS 2026 main conference, 30,709 submissions were assigned for review. The Program Committee recommended 7,900 papers for acceptance, resulting in an acceptance rate of 25.7%.
Early Failure Detection and Intervention in Video Diffusion Models
Authors: Kwon Byung-Ki, Sohwi Lim, Nam Hyeon-Woo, Moon Ye-Bin, Tae-Hyun Oh
Text-to-video (T2V) diffusion models have rapidly advanced, yet generations still occasionally fail in practice, such as low text--video alignment or low perceptual quality. Since diffusion sampling is non-deterministic, it is difficult to know during inference whether a generation will succeed or fail, incurring high computational cost due to trial-and-error regeneration. To address this, we propose an early failure detection and diagnostic intervention pipeline for latent T2V diffusion models. For detection, we design a Real-time Inspection (RI) module that converts latents into intermediate video previews, enabling the use of established text–video alignment scorers for inspection in the RGB space. The RI module completes the conversion and inspection process in just 39.2 ms. This is significantly efficient considering that CogVideoX-5B requires 4.3s per denoising step when generating a 480p, 49-frame video on an NVIDIA A100 GPU. Subsequently, we trigger a hierarchical and early-exit intervention pipeline only when failure is predicted. Experiments on CogVideoX-5B and Wan2.1-1.3B demonstrate consistency gains on VBench with up to 2.64x less time overhead compared to post-hoc regeneration. Furthermore, our pipeline is plug-and-play and orthogonal to existing techniques, showing seamless compatibility with prompt refinement and sampling guidance methods. We also provide evidence that failure signals emerge early in denoising process and are detectable within intermediate video previews using standard vision-language evaluators.
FacEDiT: Unified Talking Face Editing and Generation via Facial Motion Infilling
Authors: Kim Sung-Bin, Joohyun Chang, David Harwath, Tae-Hyun Oh
Editing a local segment in a talking head video without reshooting the entire scene remains challenging and underexplored. Given local edits, such as insertion, deletion, or substitution, talking head video editing must synthesize a replacement segment while leaving the rest unchanged. This requires variable-duration local rewriting while preserving identity, unedited regions, and boundary continuity, which standard speech-driven generation and lip synchronization do not directly address. Moreover, direct supervision is infeasible, as it requires paired videos of the same person and scene differing only in a local spoken segment, which does not exist in the real world. We instead formulate talking head video editing as facial motion infilling, a self-supervised pretext task that recovers masked facial motion from speech and surrounding motion context in ordinary video–speech pairs. The key insight is that local video editing can be simulated during training by masking a motion span and reconstructing it from speech and visible motion context. Based on this formulation, we introduce FacEDiT, a mask-controlled talking head model with local temporal attention bias and temporal smoothness regularization for improved lip–speech alignment and transition continuity. We also introduce FacEDiTBench, the first benchmark for talking head video editing, covering diverse edit types and lengths with dedicated evaluation metrics. Extensive experiments show that FacEDiT produces accurate, speech-aligned edits with strong identity preservation and seamless boundary transitions. Beyond editing, the same facial motion infilling model extends to portrait animation and lip synchronization by simply changing the mask pattern, establishing FacEDiT as a unified framework for talking head video editing and generation.
Hear, Localize, and Reason: Spatially Aware Scene Understanding for Audio-visual LLMs
Authors: Kim Sung-Bin, Lee Jung-Mok, Jinwoo Jung, Oh Hyun-Bin, Hyeonggon Ryu, David Harwath, Tae-Hyun Oh
Audio-visual large language models (AV-LLMs) have made strong progress in multimodal understanding, but they typically treat audio as monaural semantic content and therefore struggle to reason about where sounds originate and how they relate to the visual scene. Recent spatial audio-visual studies address parts of this problem, but often focus on specific abilities, such as spatial correspondence or direction and distance reasoning. In this paper, we propose HLR-AVSceneQA, a comprehensive benchmark for spatial audio-visual scene understanding. HLR-AVSceneQA evaluates whether models can jointly hear, localize, and reason by recognizing what is heard, grounding where it comes from in egocentric and allocentric views, and inferring how sound sources relate to visible, hidden, or nearby objects. We further introduce HLR-LLM, which extends a strong audio-visual foundation model with a binaural spatial audio branch. HLR-LLM is trained with a three-stage curriculum, applying chain-of-thought supervision in the final stage to help the model learn structured multi-step spatial reasoning. Experiments show that existing AV-LLMs remain limited in spatial grounding and relational reasoning, while HLR-LLM substantially improves spatial audio-visual scene understanding without sacrificing semantic audio-visual perception.