Claims Browser

Physics-integrated 3D Gaussian representations can now reconstruct deformable objects that can be simulated and rendered under explicit material models

"Physics-integrated 3D Gaussian representations now allow reconstructed deformable objects to be simulated and rendered under explicit material models."

Existing physics-integrated 3D Gaussian pipelines are limited because they assume material parameters are known or manually specified

"Existing pipelines, however, assume that material parameters are known or manually specified, limiting their applicability when these parameters must be inferred from observed object dynamics."

KnockGS can estimate elasticity and density scales of 3D Gaussian objects from their dynamics under known applied forces

"We propose KnockGS, an interaction-response PhysicalGS framework that estimates the elasticity and density scales of a 3D Gaussian object from its dynamics under a known applied force."

KnockGS recovers material scales substantially more accurately than response retrieval, global regression, or fixed default materials across five held-out material targets

"Across five held-out material targets, our method recovers the scales substantially more accurately than response retrieval, global regression, or a fixed default material"

Interaction response carries enough information to calibrate material scales in physically grounded 3D Gaussian representations

"Interaction response therefore carries enough information to calibrate material scales in physically grounded 3D Gaussian representations."

This work represents a first step toward interactive PhysicalGS systems with calibrated Gaussian assets that have consistent rendered appearance and simulated response

"Our study is a first step toward interactive PhysicalGS systems that calibrate a Gaussian asset whose rendered appearance and simulated response are consistent."

A 2-stage XGBoost-based model for optimally populating eBay's View-Item page with contextual signals achieved a 0.08% lift in overall Gross Merchandise Bought

"we present a 2 stage xgboost based model that optimally populates the VI page with signals. This approach has shown a 0.08% lift in overall GMB (Gross Merchandise Bought)"

The XGBoost-based signal optimization system increased Parts and Accessories GMB by 0.58%, primarily through increased conversion of high average price items

"0.58% increase in Parts and Accessories GMB, primarily due to increase in conversion of high average price items in online experimentation"

JEPA world model encoders with fixed-size Vision Transformer encoders are over-provisioned for simple tasks and under-provisioned for complex ones, with significant redundancy across attention heads

"Joint-Embedding Predictive Architectures (JEPAs) for world modeling typically employ fixed-size Vision Transformer encoders that are over-provisioned for simple tasks and under-provisioned for complex ones, with significant redundancy across attention heads"

Successive Capacity Growth (SCG) achieves 20.3% improvement in prediction loss over fixed small baseline with 56 times greater parameter efficiency on multi-object dynamics tasks

"On a 60-dimensional multi-object dynamics task, SCG naturally triggers depth expansion, improving prediction loss by 20.3% over the fixed small baseline with 56 times greater parameter efficiency than scaling to the fixed large model"

SCG achieves 23% improvement over fixed large models on 2D navigation tasks with a single width expansion

"on a 2D navigation task, a single width expansion yields even an 23% improvement over the fixed large model"

JEPA world model encoders can grow successively as tasks demand rather than being pre-allocated at maximum capacity, achieving significant compute and data efficiency

"JEPA world model encoders need not be pre-allocated at maximum capacity - they can grow successively as the task demands, achieving significant compute and data efficiency while maintaining representation quality"

The Sketched Isotropic Gaussian Regularizer (SIGReg) prevents representation collapse by ensuring all learned semantic dimensions remain statistically independent and aligned with the predictive objective

"The Sketched Isotropic Gaussian Regularizer (SIGReg) ensures that all learned semantic dimensions remain statistically independent and aligned with the predictive objective, preventing collapse even as the architecture grows"

SCG's adaptive encoder matches or exceeds fixed small baseline across all tested environments with zero false-positive expansions and bit-exact function preservation

"Across all three tested environments of increasing complexity, the adaptive encoder matches or exceeds the fixed small baseline, with zero false-positive expansions and bit-exact function preservation (ratio = 1.0, absolute difference = 0.0)"

Training Llama-3.2-3B costs over $1.5M at small scale

"Even at a small scale, training Llama-3.2-3B costs over \$1.5M"

Reproducing SmolLM3-3B requires over $700K in training costs

"reproducing SmolLM3-3B needs over \$700K"

Puro-2B can be trained for less than $6.9K while approaching Qwen2.5-1.5B performance

"Our best model is trained at a compute cost of less than \$6.9K and approaches Qwen2.5-1.5B performance under our evaluation protocol"

A cost-efficient, hardware-accessible, and open-source pretraining recipe has been missing from the field

"a cost-efficient, hardware-accessible, and open-source pretraining recipe has long been missing"