Auditable AI Text Detectors with Sparse Features
Turning opaque neural text detectors into concept-level, auditable classifiers.
DailyUpdated 2026-11-07 12:20 UTC23 articles
Research
Papers and results that change what is possible
Monsoon: building speech corpora as a system
Inside a five-stage pipeline for low-resource spontaneous speech that actually moves ASR metrics
Inside RadarGSOcc’s 4D radar occupancy pipeline
How RadarGSOcc turns sparse 4D radar tensors into Doppler-aware 3D semantic occupancy grids and what that means for autonomy stacks.
Inside Dexterity from Supervised Play
How DSP turns minutes of human play into hours of autonomous data and dexterous control.
Building with Varest-style semantic token compression
How semantic-aware tokenization and in-model pruning cut vision tokens ~20× while keeping most capability.
EgoLAP and language-action chains for robots
How a language-based action chain-of-thought narrows the embodiment gap between human egocentric video and robot control.
Natural language to protein structure with Prompteina
How Prompteina links text prompts to all-atom protein design and what that implies for agentic bioengineering stacks
Kernaut: agents that write kernels, safely
How Kernel Autoresearch turns kernel design into an open-ended, agentic search over valid programs.
Bi-FORK: generative surrogates for bifurcating physics
A generative latent-flow model that learns one-to-many solution maps in high-dimensional physical systems.
QF3: Off‑policy RL for flow policies in robots
How QF3 fuses flow matching and Q‑gradients to train and fine‑tune flow policies efficiently.
RL controllers for autonomous endovascular BCI access
How a Soft Actor-Critic stack navigates cerebral veins and predicts its own failure in vitro.
Building self-improving reasoning data harnesses
How recursive harness self-improvement hardens tasks without touching model weights
Inside GenCine’s 3D-Controlled Video Pipeline
How Generative Cinematographer turns a single image into an editable 3D scene for jointly authoring camera and object motion.
Inside Faynt: multi-character Melee at 5ms per move
How Faynt reaches state-of-the-art multi-character Melee play with small Transformers, clever post-training, and tight evaluation.
Closing cross‑lingual loopholes in LLM unlearning
A new 174‑language benchmark and the COVER method show how to budget your unlearning effort across languages instead of blindly retraining everything.
Loop Scaling Laws for Looped MoE in Practice
How looped transformers and sparse MoE jointly scale, and what their new scaling law implies for model design.
Verifiable rewards for controllable image generation
How VVR turns synthetic scenes into programmatically checkable rewards that transfer to natural prompts.
ClearGS: Making Gaussian Splatting Survive Messy Video
How ClearGS re-weights views and repairs frames to make 3D Gaussian Splatting robust to handheld video artefacts.
NNV3: What Builders Need From Neural Net Verification
How NNV3 extends set-based verification to new model classes, inputs, and fairness constraints.
Computation Over Geometry in RAG Systems
New results suggest semantic “sameness” is computed jointly, not stored in off‑the‑shelf embedding spaces.
Inside Underwater C3-JEPA for ROV salvage
An object-centric cross-view world model for underwater manipulation and how to actually use it in agents.
From toy math to open problems in 3 years
Frontier models are now closing real open problems in math, history, and biology; here’s the orchestration pattern builders can actually copy.
Inside DexTacWAM’s visuo-tactile world model
How DexTacWAM fuses fingertip touch with video diffusion to control a 22-DoF bimanual manipulator.
Live signals on Research
- @AnthropicAI: New Anthropic research: progress on provable inference for large language models. X · ai radar · 3 days ago · frontier 89%
- Social Humanoid: Socially Responsive Human-Humanoid Interaction arXiv · 1 days ago · frontier 90%
- Perceptive Humanoid Motion from Simulation arXiv · 2 days ago · frontier 93%
- 4D Point Splatting for mmWave Radar Micro-Doppler Differentiable Rendering arXiv · 1 days ago · frontier 91%
- GFlowQEC: Generative Flow Networks that Learn to Sample Quantum LDPC Codes arXiv · 2 days ago · frontier 87%
- Dexterous Robotic Hands in the Foundation-Model Era: A Full-Stack Survey of Hardware, Data, Cross-Embodiment… arXiv · 2 days ago · frontier 86%
- SpecCTMC: Exact Speculative Simulation of Diffusion Language Model Continuous-Time Markov Chains arXiv · 1 days ago · frontier 90%
- Weight-space programming for auditing clinical decision networks arXiv · 3 days ago · frontier 95%
- MOMASPLAT: Dynamic Novel-View Demonstration Augmentation for Mobile Manipulation arXiv · 1 days ago · frontier 86%
- A Circuit for In-Context Learning arXiv · 3 days ago · frontier 84%
- FedReason: Large Language Models as Weight-Space Meta-Aggregators for Heterogeneous Federated Learning arXiv · 1 days ago · frontier 85%
- VisionSIM: Beyond Idealized Sensors - A Multi-Modal Simulator for Robot Perception arXiv · 1 days ago · frontier 74%
- Reinforcement Learning Enables Scaling Generalist Robot Policy Improvement arXiv · 2 days ago · frontier 90%
- RM-VLM: From Natural-Language Task Descriptions to Vision-Grounded Reward Machines arXiv · 1 days ago · frontier 79%
- Data-driven discovery of intrinsic Lie point symmetries of differential equation systems arXiv · 1 days ago · frontier 80%