Research
Curated daily papers, lab research blogs and national AI research programs across the US, China, EU, UK, Japan and beyond.
Curated daily papers, lab research blogs and national AI research programs across the US, China, EU, UK, Japan and beyond.
Latest in Research
30 storiesFrom numerical proportions to analogical proportions between probabilities
Analogical proportions link four items a, b, c, d by a relation stating that ``a is to b as c is to d", a, b, c, d being the formal representation of real world…
Have You Ever Seen Them? Entity-level Membership Inference through Interrogating Large Language Models
Large Language Models (LLMs) raise growing concerns about privacy leakage and copyright compliance. Membership inference is a key tool for assessing such risks,…
IPO Finance Agent: Evaluation of LLM Financial Analysts beyond Finance Agent v2, with Automated Rubric Generation -- the Case of the SpaceX (SPCX) IPO
Finance Agent v2 (by Vals AI) has emerged as the reference benchmark for evaluating both Anthropic Claude and OpenAI ChatGPT frontier language models on financi…
PeLAP-A: Adaptive Latent Pruning for Lightweight Latent Diffusion Models
Latent diffusion models achieve strong generative performance by operating in a compressed latent space produced by a variational autoencoder (VAE). However, it…
PIVOTSBench: Evaluating Fine-Grained Interpersonal Relationship Reasoning in Multimodal Large Language Models
Humans possess an innate ability to understand fine-grained interpersonal relationships, which is central to everyday social interactions. Although such reasoni…
Minimax Quantile Lower Bounds for Interactive Statistical Decision Making with Privacy
Minimax risk and regret are expectation-based criteria and do not capture rare but consequential failures. To address this concern, we develop a $δ$-explicit mi…
Self-Evolution for Multi-Turn Tool-Calling Agents via Divergence-Point Preference Learning
Multi-turn tool-using agents must coordinate long-horizon tool sequences while tracking dialogue state and policy constraints. Existing approaches often separat…
LUMINA-26: Low-Light Understanding for Modeling and Interpreting Night-time Actions
Low-light human action recognition remains a challenging problem due to poor illumination, amplified noise, motion ambiguity, and diverse real-world scenes. Exi…
MambaADv2: Evolving Duality-enhanced State Space Model for Unsupervised Anomaly Detection
While recent advancements in anomaly detection have demonstrated the efficacy of CNN- and Transformer-based approaches, these architectures face inherent limita…
Expert Consensus on Criteria for the Automated Assessment of Laparoscopic Camera Navigation
Background: Laparoscopic camera navigation (LCN) is a critical skill, yet its current assessment typically relies on manual rating systems which are time-consum…
EML Trees Are Universal Approximators
The recently introduced EML (Exp-Minus-Log) function acts as continuous analogue of NAND gates, providing a compositional building block capable of representing…
StreamPPG: Low-Latency rPPG Estimation via Consistent Privileged Learning
Remote photoplethysmography (rPPG) estimates the blood volume pulse (BVP) signal from facial videos, enabling contact-free health monitoring. Conventional clip-…
Deep learning-based detection of cessation of breathing in pre-term infants
Apnoea of prematurity is characterised by recurrent episodes of cessation of breathing and remains difficult to detect reliably using routinely monitored physio…
RS-Gen: A Multi-Stage Agentic Framework for Reasoning and Search-Augmented Image Generation
Recent years have witnessed remarkable progress in image generation and editing, particularly regarding instruction following and visual fidelity. However, when…
PhysFlow: Frequency Decoupled with Dual-Field Rectified Flow for Remote Photoplethysmography
Remote Photoplethysmography (rPPG) enables contactless pulse estimation from facial videos, serving as a vital tool for health monitoring. However, current deep…
Transfer learning-based method for automated ewaste recycling in smart cities
Sorting a huge stream of waste accurately within a short period can be done with the support of digitalization, particularly Artificial Intelligence, instead of…
The Watermark Shortcut: How Provenance Marking Sabotages Audio Deepfake Detection
Provenance watermarking is increasingly treated as a safeguard for synthetic speech, whether built directly into speech-generation models such as Chatterbox, pr…
Ultra-Peripheral Collisions as a Nuclear-Structure Interferometer with Interpretable Multitask Deep Learning
Precise knowledge of nuclear structure is essential across fundamental physics, yet probing these structures is notoriously difficult. To address this challenge…
TooBad: Backdoor Diffusion Models with Ultra-Low Poison Rate and Imperceptible Trigger
Diffusion models (DMs), despite their impressive capabilities across a wide range of generative tasks, have been shown to be vulnerable to backdoor attacks. How…
Polynomial Dice Loss for Medical Image Segmentation
Medical image segmentation is a fundamental task for medical image processing and computer-assisted intervention, yet data imbalance and small lesion detection …
UnBias-Plus: Detect, Explain, and Rewrite Bias
Bias in natural language remains a persistent challenge in both human-written and AI-generated content, affecting domains such as journalism, education, and AI …
AOHP: An Open-Source OS-Level Agent Harness for Personalized, Efficient and Secure Interaction
AI agents are driving a new software paradigm, with the ability to autonomously call tools, extract information, manage memory, and complete tasks that span app…
Sublinearly Structured Deep Neural Networks Achieve Feature Learning Consistency for Compositional Functions
Over the past decade, deep neural networks (DNNs) have achieved remarkable success on complex machine-learning tasks, yet the theoretical foundations of their p…
Concordia: JIT-Compiled Persistent-Kernel Checkpointing for Fault-Tolerant LLM Inference
Long-running LLM agents keep valuable state resident on GPUs: KV caches, request schedulers, communication state, and sometimes online adapters. Losing this sta…
A Generative Model for Closed-Loop Microsimulation of Signalized Intersections
Traffic microsimulators rely on hand-crafted behavior models that reproduce aggregate flow but miss the heterogeneous interactions between vehicles at signalize…
Real-Time Multimodal Activity-Aware Error Detection in Robot-Assisted Surgery
Robot-assisted minimally invasive surgery improves surgical precision but introduces complexity, making technical error detection essential for ensuring patient…
Discovering Latent Groups for Robust Classification
Machine learning models exploit spurious correlations, achieving high average accuracy but failing disproportionately on underrepresented subgroups. Existing me…
CoorDex: Coordinating Body and Hand Priors for Continuous Dexterous Humanoid Loco-Manipulation
Humanoid loco-manipulation is often simplified into a stop-and-go process: walking to an object, stopping to manipulate it, and then resuming locomotion. It als…
Keep The Essentials: Efficient Reference Conditioned Generation via Token Dropping
Reference-based diffusion models enable highly controllable image generation by leveraging elements from input images to guide prompt-driven synthesis. However,…
GLM-5.2 is the step change for open agents
A capability threshold I've been carefully monitoring.…