SpecMRL improves compressed embeddings by reorganizing features via a learned spectral basis that prioritizes informative ...
AdaExploreBench evaluates whether LLM agents can actively discover hidden environmental rules and adapt to unannounced ...
🤖 GroundingPI: What foundation model does embodied AI need? 4B parameters. SOTA overall across 34 grounding benchmarks, surpassing GPT-6 Astra! By training precise perception as a native capability, ...
Author here. WebFovea is a vision-based web agent that placed 2nd in the WebRetriever Challenge 2026 (57.0/100). It works on live websites through their own UI: screenshots in, clicks and keystrokes ...
MIST separates scene setup from change execution to isolate memory failures in video world models, and M3-Agent improves ...
Add files using upload-large-folder tool about 1 year ago meta Add files using upload-large-folder tool about 1 year ago videos Add files using upload-large-folder tool about 1 year ago ...
Join the discussion on this paper page Tencent WorkBuddy Bench: A Multi-Domain Coding-Agent Benchmark with Contamination-Resistant Task Construction ...
Remote KV caching for long-context LLM serving can severely degrade latency unless the store is sharded by parallel rank, ...
OneWM unifies causal training of world and action modeling, showing that learning action-conditioned dynamics improves ...
Timestral is a family of time series foundation models for zero-shot forecasting, available in 5M, 28M, 123M, and 209M parameter versions. This repository contains the 209M checkpoint. Timestral ...
Velox accelerates long video rollouts by routing attention via geometric frustum slabs, reducing latency while preserving ...
The method converts pre-trained transformers into elastic models that adapt continuously to varying computational budgets by ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results