AI System Turns One Image Into Relightable 3D Assets
Preprint: Luce reports leading scores on several 3D-generation benchmarks, while its authors flag limits with tiny details and complex materials.
Search
2,230 results
1541–1560
Preprint links curvature to inequalities in free Langevin dynamics
A mathematical proof study describes a Bakry–Émery framework and derives conditional Poincaré and modified logarithmic Sobolev inequalities.
Sensorless Gripper Reports Lower Damage on Soft TPU Cubes
Preprint tests a controller using encoder position and motor effort, with high grasp success in firmer simulations but a sharp grasp–damage trade-off in the softest cases.
Three Coding-Agent Systems Converge, but a Trust Gap Remains
Preprint: A qualitative review of deepagents, pi and dsh finds five recurring design elements, but none offers an independently verifiable record.
PayPal preprint reports SCOUT's tool-schema context comparison
The report compares 140,200 pre-SCOUT tool-schema tokens with 1,300 production tokens in one implementation and reports an 84.8% first-result hit rate across 45 evaluable benchmark queries.
RAG tests report lower attack success with a new filter
An arXiv preprint reports lower attack success on three question-answering benchmarks, but its guarantee depends on assumptions about the retrieved documents.
WiFi system reports lower errors estimating 3D human pose
Preprint: A physics-informed system reported lower 3D pose errors on benchmarks and in an indoor zero-shot test.
AI model tops tests across four multi-subject learning datasets
Preprint: LT-MKT combines cognitive-load modeling with cross-domain knowledge transfer in an AI learning model.
Three mathematical views of canonical bases are shown to agree
A preprint reports a theoretical result linking the equality to open Richardson varieties and a type-A polytope criterion.
Live-ad system reports 16.1% revenue lift in randomized test
A preprint reports a multi-week experiment on Kuaishou's production traffic covering more than 40 million users, with TAGR outperforming the DLRM baseline on revenue and engagement rates.
Robot-vision model shows more predictable dynamics with physics data
Preprint: Training with paired visual and privileged physical trajectories was associated with lower forecast drift and higher average control success in simulated robot tasks.
AI alignment study finds welfare costs as harm limits tighten
Preprint examines social-choice mechanisms for AI systems affecting many people and shows that tighter welfare floors can carry rising average-welfare costs.
Finite-element proposal expands mesh options for interface problems
Preprint: A nodal immersed finite-element construction is analyzed on unfitted quadrilateral and hexahedral meshes and tested in two numerical examples.
AI agent scores 65% on meeting inference questions, versus 25%
Preprint: A graph-based system outscored text retrieval on AMI and was also tested for citations, human ratings and simulated noise, without formal significance testing.
Larger AI memory model linked to better robot control in tests
Preprint: PonderPounce reported 60.83% RoboMME success at base scale and 75.54% with 9x data in simulated tests.
Three-way compression reports speed and accuracy gains
Preprint results combine sparsity, quantization and low-rank methods across LLM training and deployment experiments, while hardware portability remains unproven.
Mesh-free model reproduces complex crack patterns in tests
Preprint: A neural solver matched key finite-element fracture curves and reproduced branching, coalescing and hole-driven cracks, but cost roughly an order of magnitude more per load increment.
Fault-driven tests linked to higher scores for a code model
Preprint: A Qwen3-32B study reports the top listed benchmark scores, but residual invalid tests and missing variance estimates temper the result.
AI screens 46,061 rejected galaxies for paired nuclei
Preprint: A deep-learning model produced 29,605 candidates, but the authors say the list is not a catalogue of confirmed systems with two active nuclei.
Staged AI Agent Tops Multi-Turn Tool Tests Across Model Sizes
This arXiv preprint reports OODA-Tool's clearest gains on tasks that require carrying state across turns, with higher latency for its four-call design.