AI agents increasingly carry out long-horizon professional work, but their evaluations rarely require a finished creative deliverable. To this end, we introduce Timeline-Bench, a benchmark of 56 real video-editing tasks, each asking an agent to turn raw production material into a finished video. Tasks range from select...
OPIS is introduced, an input-grounded benchmark that strictly anchors the assessment to a fixed set of object instances from the initial observation for evaluating multi-object memory in video world models and demonstrates that preserving the particular object instances in the input is considerably harder than generati...
Hao Wang, Tao Yu, Liu-Zhou Zhang et al.· 0 citations
Visual token compression reduces the inference cost of Large Vision-Language Models (LVLMs). However, aggregate robustness measures do not reveal whether a particular adversarial failure is induced by compression or inherited from the underlying model. We define a compression-specific failure (CSF) as an adversarial in...
Qian-Kun Li, Yuechen Zhang, Bo-Wen Chen et al.· 1 citation
It is proposed that intermediate layer tokens from vision encoders should be considered for effective visual token pruning, as semantic focus shifts across layers, with middle-layer tokens capturing more detailed object-centric information that deeper layers may abstract away.
Tian-Xiang Chen, Zhentao Tan, Zi Ye et al.· IEEE Transactions on Pattern...· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
This work proposes $\delta$-Vision, which replaces repeated Transformer evolution of visual tokens with lightweight low-rank adapters that construct layer-wise visual memories while preserving all visual tokens for text retrieval, and achieves higher accuracy than visual token pruning baselines at comparable or lower c...
Jing-Di Lei, Junxian Li, Di Zhang et al.· 0 citations
This work proposes Action Upcycling, a training-free algorithm that reuses actions the policy would otherwise discard, without accessing model internals or drawing extra samples, and finds that discarded actions stay close to their replanned versions as long as the action velocity remains smooth.
Taesung Kwon, Jangho Park, Sunwoo Park et al.· 0 citations
EviSplat is introduced, which preserves individual observation features as evidence for later text queries within class-agnostic 3D instances that represent objects, object parts, or background regions and learns a distribution describing which visual appearances its observations support.
Sung-Ho Moon, Kota Shimomura, Junwoo Park et al.· 0 citations
ESTHER is proposed, a model whose stereo geometry, temporal reasoning, and output representation are designed for wearable egocentric stereo, and shows state-of-the-art accu?racy, superior external generalization, and robustness to the missing views, dropped frames, and lighting and motion blur extremes of real egocen...
Hong-Yu Ma, Hai-Rong Qu, Shi-Qi Zhao et al.· 0 citations
This work introduces CoHuB (Collaborative Multi-Humanoid Benchmark), a simulation benchmark for multi-humanoid collaboration under egocentric visual observations and provides a foundation for developing and evaluating multi-humanoid collaboration policies.
Hyunji Park, Jebeom Chae, Minwoo Park et al.· 0 citations
These results show that reliable scene-text recognition requires VLMs to balance visual character evidence with contextual information, preserving clear text while using context mainly when the visual evidence is uncertain.
This work revisits model completeness: how well the concepts can reproduce the model's outputs, and shows that model incompleteness of the concepts can be bounded by the autoencoder's reconstruction error.
Vojtech Kur, A. Kukucka, T. Brázdil et al.· 0 citations
Real-world driving is inherently multi-agent, yet most existing driving world models generate observations from a single ego vehicle. Independently extending them to multiple vehicles does not ensure that different agents observe a consistent shared world. We present CoDrive, a cross-vehicle, multi-view driving video g...
Yu Meng, Bai-Ning Zhao, Jun-Tao Wu et al.· 0 citations
Professor Paris Smaragdis develops computers with superhuman hearing for applications like speech recognition, music understanding, and environmental monitoring.
Exploring how generative AI could make machine vision more accessible to businesses. The post GenEye in a Box: Making Machine Vision Something You Can Just Ask For appeared first on GPT-Lab.
Jennifer Neville did not want to go into computer science—but that’s exactly where she landed. Neville discusses the starts and stops that led to her professional sweet spot and her work identifying “surprising failures” making it hard for AI to handle complexity. The post What AI gets wrong and what failure teaches us appeared first on Microsoft Research.
Computer scientist, entrepreneur, and philanthropist will collaborate with the MIT Schwarzman College of Computing to advance AI and scientific discovery.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
