Browse and export your curated research paper collection
[object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object] 11/10/2026 huggingface
generative modelsUnderstanding 4D scenes is a core challenge in visual intelligence, requiring models to jointly capture scene geometry, appearance, and dynamics from partial observations. However, existing approaches are subdivided into feedforward models for direct geometric prediction, and generative models for v...
[object Object], [object Object], [object Object], [object Object], [object Object] 11/10/2026 huggingface
roboticsPretrained video diffusion models (VDMs) offer a powerful foundation for World Action Models (WAMs), which jointly predict robot actions and future observations. Building such models requires injecting low-dimensional robot signals (e.g. proprioception, actions, and values) into a latent space shape...
[object Object] 11/10/2026 huggingface
natural language processingStreaming speech recognizers output a word only after the speaker has finished it, typically 90-400 ms later. For a voice agent every millisecond counts: the sooner the words are outputted, the sooner the agent can start a search or plan its reply. We present Earlybird, a 29M-parameter streaming rec...
[object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object] 11/10/2026 huggingface
roboticsWe describe our solution for the 2026 BEHAVIOR Challenge: 100 long-horizon household tasks in the OmniGibson simulator. We placed 9th on the final leaderboard, the only independent team in the top 10. The core of the solution is a single vision-language-action (VLA) model, one checkpoint for all 100...
Howard Zhang, Chuck Arvin, Logan Brown, Mihir Bhatia, Neelu Choudhary, Lily Miao 11/10/2026 arxiv
natural language processingDeploying LLM-based analytics agents in enterprise settings requires evaluation frameworks that can reliably detect failures across complex, multi-tool workflows. We present a three-phase comparative study of three evaluation frameworks, each representing a distinct evaluation paradigm (trace-based ...
Zijian Zhang, Rizhen Hu, Jiangweizhi Peng, Shiyang Li, Sujay Bhatt, Sihan Zeng, Mingyi Hong 11/10/2026 arxiv
reinforcement learningReinforcement learning with verifiable rewards (RLVR) produces rich training experience, yet outcome rewards reduce each attempt to a single number and leave most of this information unused. Training-time scaffolds, such as strategies or hints added to the prompt during training, offer a natural way...
Adi Mashiach 11/10/2026 arxiv
multimodal learningFoundation models trained on large unlabeled corpora develop emergent capabilities, tasks that go beyond the training objective. We extend this paradigm to multimodal biology with Bonbon, a foundation model for molecular interactions trained on approximately 3.2 trillion tokens of paired protein-lig...
Ziang Liu, James J. Kim, Yijia Dai, Jennifer J. Sun 11/10/2026 arxiv
machine learningLLM agents are increasingly used for open-ended, data-driven scientific discovery, yet most of them evaluate hypotheses pointwise, testing an empirical claim $h$ only against its complement $\neg h$. When evidence rejects $h$, the agent learns that one explanation is unlikely but not which alternati...
Tanishq Rachamalla, Srishti Kaushik, Muhammad Attique Khan, Gustau Camps-Valls, Swalpa Kumar Roy 11/10/2026 arxiv
computer visionCross-sensor remote sensing image retrieval aims to find scenes with the same content across heterogeneous sensors, such as SAR and optical or panchromatic (PAN) and multispectral (MS) imagery, without manual labels. Existing self-supervised methods either reconstruct sensor-specific pixel detail, a...
[object Object], [object Object] 11/10/2026 huggingface
natural language processingWeight-space programming, introduced in recent MIT work by Takehi et al., enables a frontier LLM agent to read a network's weights and write a repair. Their GPT-6 Astra agent corrected the reasoning loops of Qwen3.5-0.8B without gradients, using 158 agent turns, 89.7 million tokens, and 50 forward-p...
Preparing your export...