Pashto
PulseAugur coverage of Pashto — every cluster mentioning Pashto across labs, papers, and developer communities, ranked by signal.
4 day(s) with sentiment data
-
New Beckmann World Models improve action-conditioned prediction accuracy
Researchers have introduced Beckmann World Models (BWM), a novel approach to learning action-conditioned world models for predicting future states in planning and policy evaluation. BWM directly learns a map from noise,…
-
New latent world model enhances embodied planning with associative memory
Researchers have developed a new memory-enhanced latent world model designed to improve embodied planning capabilities. This model integrates a content-addressable memory bank with JEPA-style prediction, allowing it to …
-
New research advances robot world models for efficient planning and control · 10 sources tracked
Recent research explores advancements in world action models (WAMs) for robotics and agent planning. WAM-Cache and WAMJET focus on accelerating inference by optimizing key-value reuse and employing agentic harnesses for…
-
New methods enhance AI agent planning with robust visual representations
Researchers have developed new methods to improve the robustness and planning capabilities of latent world models used in AI agents. The first approach, JEPA-Bisim, introduces a bisimulation encoder to enforce control-r…
-
LePlanner controller offers faster, amortized planning for world models
Researchers have developed LePlanner, a novel amortized controller designed to improve planning efficiency in world models. This iterative approach learns to construct and refine action sequences using a frozen world-mo…
-
New JEPA world model enhances robotic planning with state alignment
Researchers have developed a new end-to-end Joint Embedding Predictive Architecture (JEPA) world model designed to improve robotic planning by grounding learned representations in physical reality. This model augments l…
-
New LpWM model uses sparse representations for improved AI planning
Researchers have introduced LpWorldModel (LpWM), a new JEPA model that utilizes Rectified Distribution Matching Regularization (RDMReg) to encourage sparse representations. This approach contrasts with traditional metho…
-
New research proposes world-model cascade evaluation protocol
A new research paper introduces a novel evaluation protocol for world-model cascades, focusing on how a medium-level model can predict when switching to a more computationally intensive full model would improve decision…
-
LLMs improve biomedical translation for low-resource Arabic-script languages
Researchers have explored cross-lingual transfer learning to improve machine translation for low-resource Arabic-script languages in the biomedical domain. By using Arabic and Persian as pivot languages, they fine-tuned…
-
New research improves latent world models for robotics planning · 2 sources tracked
Two new research papers introduce novel approaches to enhance latent world models for improved planning in robotics and control tasks. The first paper, DWM, proposes a method to separate action-driven transitions from a…
-
Hierarchical planning shows mixed results for LeWorldModel control tasks
Researchers have investigated the effectiveness of hierarchical planning in the LeWorldModel for long-horizon goal-conditioned control tasks. Their extension, Hi-LeWM, freezes a pretrained low-level LeWM and adds a high…
-
New CCBENCH framework reveals LLMs struggle with cultural competence
Researchers have developed CCBENCH, a new framework to evaluate the cultural competence of large language models (LLMs). This framework assesses how well LLMs can infer and adapt to users' cultural values, rather than r…
-
New J-LAW framework merges localization and world modeling for enhanced AI planning
Researchers have introduced J-LAW, a novel approach that jointly optimizes metric object poses and latent world states for improved planning and localization. This coupled factor graph framework integrates classical Sim…
-
PRISM framework enhances robot world model action sampling
Researchers have developed PRISM, a novel framework for improving action sampling in world models for robotics. PRISM extracts action intuition directly from the world model's own learned representations, avoiding the n…
-
AI world models gain long-horizon planning via latent planners
Researchers have developed new methods for long-horizon planning in world models, addressing limitations of existing techniques. One approach, FF-JEPA, uses a hierarchical structure with two forward dynamics models, inc…
-
New Fisher-Preserving Guidance Enhances Diffusion Model Navigation
Researchers have developed a new training-free inference method called Fisher-Preserving Guidance (FPG) to improve the reliability and efficiency of diffusion models in visual navigation tasks. This method helps prevent…