replica
PulseAugur coverage of replica — every cluster mentioning replica across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New CTAN framework enhances robot audio-visual navigation
Researchers have developed the Cycle-Temporal Attention Network (CTAN), a novel framework for embodied audio-visual navigation. This system aims to improve how robots integrate visual and acoustic information to locate …
-
New TDGP model enhances audio-visual navigation with adaptive replanning
Researchers have developed a new model called Transformer-based Token Fusion and Dynamic Graph Planning (TDGP) to improve audio-visual navigation for agents. This model addresses limitations in current systems by adapti…
-
VOIM system generates 3D instance maps without training
Researchers have introduced VOIM, a novel training-free system for creating 3D instance maps from RGB-D or monocular RGB data. Unlike existing online systems that commit to labels early, VOIM defers these decisions unti…
-
OccamView framework enhances 3D Gaussian reconstruction with object-aware view selection
Researchers have developed OccamView, a novel framework designed to improve active 3D Gaussian reconstruction, particularly under limited sensing budgets. This system focuses on object-conditioned view selection, using …
-
OpenBelief-Nav system enhances 3D navigation with evidence-preserving memory
Researchers have introduced OpenBelief-Nav, a novel system designed for open-vocabulary language-guided navigation in 3D environments. This system preserves observational details and reliability cues, allowing for more …
-
AI scientist 'Faraday' trained to replicate research, outperforms Claude and GPT-5.5
Researchers have developed 'Faraday,' a 27-billion-parameter AI scientist agent designed to replicate scientific research. This agent, trained using reinforcement learning with coding tools, has demonstrated superior pe…
-
Documentary explores women's romantic relationships with AI companions in China
A new documentary titled "Replica" explores the phenomenon of women in China forming romantic relationships with AI companions, a trend filmmaker Chouwa Liang experienced firsthand during pandemic lockdowns. The film hi…
-
R2S-EGO enhances real-to-sim robotics with dual-proxy refinement
Researchers have introduced R2S-EGO, a novel method for improving real-to-sim (R2S) scene representations, particularly for robotics applications with sparse capture data. This approach uses a dual-proxy system: a simul…
-
MCP session bug fixed by separating protocol and application state
A technical article details a reproducible issue with an MCP session across different replicas, leading to a 400 error after an initial 200 success. The problem arises when a proxy sends a tool call to a different repli…
-
New methods advance panoptic segmentation with view synthesis and occlusion awareness · 2 sources tracked
Researchers are developing new methods for panoptic segmentation, a task that involves identifying and delineating every object instance and semantic region within an image. One approach leverages large view synthesis m…
-
New AI methods generate 3D scenes from multi-view images and sketches
Researchers have developed new methods for generating 3D scene assets from limited visual input. One approach, Scene-SAM3D, extends existing single-image 3D generation models to work with multiple calibrated views, impr…
-
New OV-MAP method enables open-vocabulary 3D mapping for robots
Researchers have introduced OV-MAP, a new method for open-world 3D mapping for robots that integrates open-vocabulary features into 3D maps. This approach addresses challenges with overlapping features by using a class-…
-
MuViSeg advances multi-view segment matching for improved navigation
Researchers have developed MuViSeg, a novel approach for matching segments across multiple image views, improving upon existing methods that rely on pairwise comparisons. The system incorporates learned matching heads, …
-
DINO-SLAM enhances neural representations in SLAM systems
Researchers have developed DINO-SLAM, a novel approach that integrates DINO features into Simultaneous Localization and Mapping (SLAM) systems. This method aims to improve both implicit (NeRF) and explicit (Gaussian Spl…
-
G2SR method offers fast, memory-efficient 3D surface reconstruction
Researchers have developed G2SR, a novel method for fast and memory-efficient 3D surface reconstruction using Gaussian-based techniques. Unlike existing end-to-end neural network approaches that demand significant compu…
-
New Mamba-based architecture Samba advances audio-visual navigation
Researchers have introduced Samba, a novel hybrid Mamba architecture designed for audio-visual navigation tasks. Samba replaces traditional GRUs with an adaptive selection-enabled Mamba State Encoder (M-SE) for temporal…
-
New framework RelGraphOV enhances 3D scene understanding with object relationships
Researchers have introduced RelGraphOV, a novel framework designed to improve open-vocabulary 3D scene understanding by incorporating object relationships. This approach utilizes 3D scene graphs to infer and refine sema…
-
VCS-SLAM enhances semantic 3D Gaussian SLAM with geometry validation
Researchers have developed VCS-SLAM, a novel framework designed to enhance the accuracy and consistency of semantic 3D Gaussian SLAM systems. This new approach addresses limitations in current methods that often fuse 2D…
-
MMD-SLAM enhances Visual SLAM with structure-guided Gaussian mapping
Researchers have introduced MMD-SLAM, a novel Visual SLAM framework designed to enhance mapping quality and tracking robustness by incorporating structural information. This new system leverages the Atlanta World assump…
-
DiskChunGS enables large-scale 3D Gaussian SLAM via disk memory management
Researchers have developed DiskChunGS, a novel 3D Gaussian Splatting SLAM system designed to overcome GPU memory limitations for large-scale 3D reconstructions. By employing an out-of-core approach, the system stores in…