A general vision-language model can serve as a multimodal reranker via single-pass choice questions, matching or exceeding ...
Matrix-Game 4.0 separates game logic from visual synthesis via an executable engine and autoregressive video renderer, ...
SolarRenderer turns any engine's untextured structure pass into a finished, styled video, guided by a reference first frame.
MMEnterprise-Bench evaluates this challenge with 1,613 questions across 30 simulated collaboration projects, grounded in ...
🤖 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 ...
What changes when memory, exact execution, and contextual computation can be developed and updated separately? This research grew out of experiments showing that useful language modeling can emerge ...
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 ...
MIST separates scene setup from change execution to isolate memory failures in video world models, and M3-Agent improves ...
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 ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results