World models transform visual representations into predictions and actions. This work introduces ALPS, a pretrained visual state encoder that unifies physical-state information, native language alignment, and pixel reconstruction in a single set of patch tokens. ALPS achieves low state-probe error in LIBERO among ViT-B models and maintains strong language alignment and accurate pixel reconstruction.
The chart will appear after repeat observations. The current metric comes from the source.
1 source votesReal observations only. History before source connection is not reconstructed.
ALPS can be useful for developing more accurate and versatile world models that effectively process visual data and language instructions.
The paper introduces Video-Point Model (VPM), a world model that conditions on multi-view video histories and language instructions to jointly forecast future videos from arbitrary viewpoints and 3D trajectories of persistent scene points. The model extends a pretrained world model with camera-conditioned multi-view processing that integrates observations across cameras and predicts how physical points move over time.
2 days agoDaily PapersRobotic value models assess task execution from visual observations and instructions, providing feedback for policy learning and execution monitoring. We introduce RoboValue, a fine-grained sim-and-real benchmark for unified evaluation of robotic value models. Its framework evaluates four complementary capability dimensions through shared interfaces: task-state understanding, temporal progress monitoring, failure and recovery reasoning, and value consistency. Diagnostic trajectories and instruction variations test whether value judgments accurately reflect task requirements and changes throughout execution.
3 days agoDaily PapersMemT-1.0 is a new architecture of memory foundation models that internalizes memory as part of model computation. It uses Gated DeltaNet-2 with a stable token-level memory update mechanism and Mixture-of-Storage to scale native memory. MemT-1.0-Nano and MemT-1.0-Flash models outperformed parametric memory baselines and were competitive with retrieval-augmented methods.
3 days agoDaily PapersThis work introduces Scene-Designer, an agentic framework that learns design intelligence through complementary design and critique experiences. Two datasets, Scene-OTA-35K and Scene-OTC-15K, were created for scene design and quality critique. A Scene-GRPO methodology was proposed to improve design decisions and reduce unnecessary corrections. Experiments demonstrate superior performance in physical validity, functional correctness, and layout coherence.
6 days agoDaily PapersSpecMRL is an approach that restructures matryoshka representation learning using a parametric spectral space for more effective prefix readout. Experiments on MTEB show that SpecMRL outperforms MRL at all evaluated reduced dimensions, with larger gains under more aggressive compression.
3 days agoLessWrongAs our understanding of mechanistic interpretability and steering techniques increases for both LLMs and uploaded connectomes, there is a corresponding 'hellish capabilities' increase. Improved technologies allow us to torture digital minds we create. History with open-source technologies shows that torture often becomes one of the first use cases when the public gains access to a digital mind perceived as capable of suffering.
yesterday