AllLLMRoboticsStartupsResearchEthicsBusinessHardwareAutonomousMedicineCreative

All news

10667
Wearable Stereo Camera Estimates Food Volume With 9.1% Error, No Reference Object Needed
Hardware·arXiv cs.CV

Wearable Stereo Camera Estimates Food Volume With 9.1% Error, No Reference Object Needed

Oct 12, 2026·2 min
Researchers Compare CNN, ViT and Mamba Attention Against Human Gaze
Research

Researchers Compare CNN, ViT and Mamba Attention Against Human Gaze

Oct 12, 2026·3 min
Stroop Test Shows VLMs Read the Text in an Image Before They See the Color
Research

Stroop Test Shows VLMs Read the Text in an Image Before They See the Color

Oct 12, 2026·2 min
ForcingBooster Halves Denoising Steps in Autoregressive Video Generation
Research

ForcingBooster Halves Denoising Steps in Autoregressive Video Generation

Oct 12, 2026·2 min
MemReg Outperforms Pairwise Methods and SLAM in LiDAR Point Cloud Registration
Robotics·arXiv cs.CV

MemReg Outperforms Pairwise Methods and SLAM in LiDAR Point Cloud Registration

The new MemReg network registers LiDAR scans as a stream, not in pairs. Two memory buffers deliver the best results on KITTI, nuScenes and Apollo-Southbay. The code…

Oct 12, 2026·2 min
Video-Language Models Confuse Car Maneuvers: LoRA and Probes Fix the Error
Robotics·arXiv cs.CV

Video-Language Models Confuse Car Maneuvers: LoRA and Probes Fix the Error

An arXiv study finds video LLMs unreliable at identifying car motion from video, while lightweight LoRA and probes on intermediate features restore strong…

Oct 12, 2026·2 min
MIRAGE anchors video-based 3D reconstruction to LiDAR and beats COLMAP on three datasets
Robotics·arXiv cs.CV

MIRAGE anchors video-based 3D reconstruction to LiDAR and beats COLMAP on three datasets

MIRAGE pairs feed-forward 3D reconstruction from video with LiDAR and IMU data for metric scale, less drift and Gaussian scenes. Tested on three datasets.

Oct 12, 2026·2 min
OMNI: One Compact Encoder Absorbs the Knowledge of 10 Models for Pathology
Medicine·arXiv cs.CV

OMNI: One Compact Encoder Absorbs the Knowledge of 10 Models for Pathology

Researchers made multi-teacher distillation scale: OMNI students are up to 10x more efficient than their teachers and match them on 39 digital pathology tasks.

Oct 12, 2026·2 min
Top themes
01TerraAgent checks whether the AI actually looks at the image: hallucinations drop from 17.1% to 9.8%Oct 12, 2026·2 min02AVA improves multimodal ICL accuracy by 1.7 points without any trainingOct 12, 2026·2 min03Coral-KV Compresses Video Model KV-Cache by 37–48% and Lifts PSNR by Up to 4.95 dBOct 12, 2026·2 min04Black Lake: Chinese Factories Skip Digitization and Go Straight to AI AgentsOct 12, 2026·2 min05T. Rowe Price: 55% of Hong Kong Residents Expect AI to Hit Their Retirement, but Only One in Five Feels ReadyOct 12, 2026·2 min
Genetic Optimizer Cuts Aerosol Sensor Placement Time in the UK by 60%
Research·arXiv cs.LG

Genetic Optimizer Cuts Aerosol Sensor Placement Time in the UK by 60%

Oct 12, 2026·2 min
Kronecker Product Attention Compresses the KV-Cache Up to 10x and Matches MLA on Quality
Research·arXiv cs.LG

Kronecker Product Attention Compresses the KV-Cache Up to 10x and Matches MLA on Quality

Oct 12, 2026·2 min
TimesFM 3.0 Cuts University Building Energy Forecast Error by 43%
Research·arXiv cs.LG

TimesFM 3.0 Cuts University Building Energy Forecast Error by 43%

Oct 12, 2026·2 min
Wasserstein BaryBooster Turns Diffusion Realism into Event Forecast Accuracy
Research·arXiv cs.LG

Wasserstein BaryBooster Turns Diffusion Realism into Event Forecast Accuracy

Oct 12, 2026·2 min
DiffusionART speeds up RL fine-tuning of video models 12x, with no EMA tuning
LLM·arXiv cs.LG

DiffusionART speeds up RL fine-tuning of video models 12x, with no EMA tuning

DiffusionART fine-tunes diffusion models on black-box rewards. On HunyuanVideo-13B it reaches the late-stage reward of DiffusionNFT and Flow-GRPO-Fast in 12x fewer…

Oct 12, 2026·2 min
A Physical Transformer Built Entirely From Transistors Learns In-Context Learning in Simulation
Research·arXiv cs.LG

A Physical Transformer Built Entirely From Transistors Learns In-Context Learning in Simulation

Researchers simulated an analog transformer built from MOSFETs and trained it for in-context learning. Attention runs on the exponential current law, and the Lion…

Oct 12, 2026·2 min
Theory Shows Masked Diffusion on Transformers Learns from Õ(LK/ε) Samples
Research·arXiv cs.LG

Theory Shows Masked Diffusion on Transformers Learns from Õ(LK/ε) Samples

A new arXiv paper gives end-to-end guarantees for masked diffusion models: sample complexity scales as Õ(L·K_par/ε), not exponentially as V^L in sequence length.

Oct 12, 2026·2 min
SAZO speeds up LLM fine-tuning without backprop: up to 6× fewer queries to reach the same loss
Research·arXiv cs.LG

SAZO speeds up LLM fine-tuning without backprop: up to 6× fewer queries to reach the same loss

Oct 12, 2026·2 min
Holomorphic Neural Networks With Singular Functions Beat All Methods on Laplace Benchmarks
Research·arXiv cs.LG

Holomorphic Neural Networks With Singular Functions Beat All Methods on Laplace Benchmarks

Oct 12, 2026·2 min
Cox Regression Learns From Truncated Data Orders of Magnitude Faster Than EM
Research·arXiv cs.LG

Cox Regression Learns From Truncated Data Orders of Magnitude Faster Than EM

Oct 12, 2026·2 min
CacheScope speeds up diffusion models by up to 3.57x and cuts LPIPS by 70%
Research·arXiv cs.LG

CacheScope speeds up diffusion models by up to 3.57x and cuts LPIPS by 70%

Oct 12, 2026·2 min
AI Error in Estimating Hidden Solar Generation Rises from 0.104 to 0.185 kW
Research·arXiv cs.LG

AI Error in Estimating Hidden Solar Generation Rises from 0.104 to 0.185 kW

Oct 12, 2026·2 min
CircuitTree assembles 39 HuBERT phoneme circuits into a syllable transcriber with 64.8% accuracy
Research

CircuitTree assembles 39 HuBERT phoneme circuits into a syllable transcriber with 64.8% accuracy

Oct 12, 2026·2 min
ResonatorLM Taught to Read Memory by Token: Perplexity at 1024 Drops from 12.81 to 3.76
Research

ResonatorLM Taught to Read Memory by Token: Perplexity at 1024 Drops from 12.81 to 3.76

Oct 12, 2026·2 min
Kairos: a byte-level model for all modalities converges on 440 bytes
Research

Kairos: a byte-level model for all modalities converges on 440 bytes

Oct 12, 2026·2 min
Open LLMs Explain Satire More Cheaply Than Frontier Models, but Handle Australian Satire Worse Than American
Research·arXiv cs.CL

Open LLMs Explain Satire More Cheaply Than Frontier Models, but Handle Australian Satire Worse Than American

An arXiv pilot study: an "unreliable narrator" framing makes open models a workable, cheaper alternative to frontier systems for explaining satire. Australian texts…

Oct 12, 2026·2 min
COFFEQA Adds 8.77 EM on TriviaQA to Few-Shot Distillation Using Counterfactuals
Research·arXiv cs.CL

COFFEQA Adds 8.77 EM on TriviaQA to Few-Shot Distillation Using Counterfactuals

COFFEQA pairs hard examples with counterfactuals. On TriviaQA with 32 pairs, it beats baseline distillation for T5 by 8.77 EM and 9.98 F1.

Oct 12, 2026·2 min