AcuityBench Exposes Miscalibrated Clinical Triage Uncertainty
A 914-case benchmark tests 12 models across four care levels, showing that conversational triage trades less over-triage for more under-triage.
Oct 11, 20264 min2605.11398
Computer Science
Research across all areas of computer science, from theoretical foundations to applied systems.
Sort:
Kandinsky 6.0 Improves Its Predecessor’s Synchronized Video
A bidirectional dual-stream diffusion transformer couples a pretrained video model with a new audio stream to generate five-second clips with 44 kHz sound.
Oct 8, 20265 min2610.05608
VoiceChat Preserves Turn Taking With Native Tool Calls
A streaming speech stack separates response text, function calls, transcription, and synthesis, reaching 82.5% tool-selection F1 while maintaining interruption handling.
Oct 4, 20265 min2609.21967
HERO Puts Acquisition Robustness at the Center of Pathology Pretraining
A ViT-G/14 pathology encoder combines DINO and iBOT pretraining with high-resolution Gram anchoring, targeting reliable representations across center, scanner, and stain variation.
Oct 2, 20263 min2609.35943
Humans and LLMs Split Theory-Building Strengths
A blinded comparison of 25 LLMs and 73 scientists finds stronger individual AI performance but more prediction-efficient, aggregable human theories.
Sep 29, 20264 min2609.32562
PhysBrain 1.5 Unifies Perception, Action, and Prediction
An 8B autoregressive model turns language, end-effector motion, and visual targets into one token stream, reaching a 72.5 average across 28 embodied benchmarks.
Sep 27, 20264 min2609.14973
CogGym Measures the Gap Between Models and Human Judgments
A unified evaluation of 50 language models across 258 cognitive experiments finds improving model--human fit, but a substantial gap from human reliability remains.
Sep 22, 20263 min2609.21259
DeepSeek Cuts KV Cache Footprint Fourfold
A causal encoder-decoder MoE pairs cross-layer sparse-attention reuse with FP4 caching to reduce global context memory to 890 bytes per token.
Sep 19, 20264 min2609.19969
Listwise Generation Raises Short-Video Engagement in Existing Rankers
LIGE-GR adds causal list context, a list-level value function, and RL beam decoding to existing rankers, raising Reels time spent by 1.14%.
Sep 17, 20264 min2609.18148
MinerU-Chem Reports 93.02% Exact Molecular Recognition
A chemistry-focused extension to MinerU converts document regions into molecule and reaction records, outperforming the evaluated GPT-5.6-Sol comparison on a SMILES benchmark subset.
Sep 14, 20262 min2608.03525