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 storiesBreaking Shortcut Learning for Cross-Trial EEG-Guided Target Speech Extraction via Two-Stage Training
Recent end-to-end models for EEG-guided target speech extraction report impressive results, underscoring potential for neuro-steered hearing technologies. Howev…
Automated Residual Plot Assessment With the R Package autovi and the Shiny Application autovi.web
Visual assessment of residual plots is a common approach for diagnosing linear models, but it relies on manual evaluation, which does not scale well and can lea…
LLMs Prompted for Legal Context Object More: Overrefusal from Small On-Premises LLMs in Criminal Legal Context
While the validity of LLMs' use in the legal context remains subject to ethical and legal debate, legal professionals are already experimenting with personal LL…
ParaPairAudioBench: Paralinguistic Pairwise Audio Benchmark for LALM-as-a-Judge
Large Audio-Language Models (LALMs) have been widely used as judge models for the automatic evaluation of generated speech. However, prior approaches predominan…
Can Scale Save Us From Plasticity Loss in Large Language Models?
The loss of plasticity - the ability of a network to learn new information after having already learned older information - is a fundamental challenge in creati…
CANDLE: Character-level Arabic Noise Deduplication using Lightweight Encoder
Handling repeated characters in text can be tricky, since they can represent either the correct spelling of a word or informal character elongation often seen i…
FLUX3D: High-Fidelity 3D Gaussian Generation with Diffusion-Aligned Sparse Representation
Sparse voxel representation has emerged as a scalable foundation for image-to-3D Gaussian Splatting (3DGS) generation, yet current methods struggle to preserve …
Phoneme-Level Mispronunciation Screening in Polish-Speaking Children with an Explainable Assistant
Early identification of speech sound errors in children is often limited by access to specialists, motivating lightweight screening tools that can operate outsi…
Decoupling Reconnaissance and Exploitation: Measuring the Capability Boundaries of LLM-Based Web Penetration Testing
Large Language Models (LLMs) have shown promise for automated penetration testing, yet existing end-to-end black-box evaluations are highly susceptible to error…
Introducing corpora Hlava Cor and Hlava AD: Human Label Variation in Coreference and Discourse Relations
As previous research on annotator disagreement in discourse phenomena has shown, understanding text coherence varies considerably from one individual to another…
Interpretable Concept-Guided Polynomial Tabular Kolmogorov-Arnold Network for EEG-Based Mild Cognitive Impairment Detection
Early and scalable detection of mild cognitive impairment (MCI) remains an unresolved clinical challenge. Existing EEG-based screening approaches are constraine…
Rate-Aware Quantum-Inspired Trajectory Learning for Interference-Limited Multi-UAV Networks
Unmanned aerial vehicle (UAV) can provide on-demand, high-capacity connectivity in disaster and normal situation. However, it faces a challenge of curse of dime…
SFL-MTSC: Leveraging Semantic Frame-Level Multi-Task Self-Consistency for Robust Multi-Intent Spoken Language Understanding
Prompt-based spoken language understanding (SLU) with large language models (LLMs) often suffers from inconsistent intent--slot structures due to decoding stoch…
EMA-FS: Accelerating GBDT Training via Gain-Informed Feature Screening
Gradient Boosted Decision Trees (GBDT), exemplified by LightGBM, spend a dominant fraction of training time -- typically 65-70% -- constructing per-feature hist…
Finding the Time to Think: Learning Planning Budgets in Real-Time RL
Deliberating takes time. In real-time settings, that time is not free. Standard reinforcement learning (RL) sidesteps this as the environment waits indefinitely…
A Causal Foundation Model for Structure and Outcome Prediction
We introduce TabPFN-CFM, a causal foundation model that can handle multiple causal problems. TabPFN-CFM predicts both causal structure and outcomes from observa…
Multipath Adaptive Gated Bottleneck Latent ODE with Raman Data Fusion for Cell Culture Process Forecasting
Mammalian cell-culture processes underpin the manufacture of many biopharmaceuticals, yet keeping a run on track is hard: critical process parameters drift over…
Heavy-Ball Q-Learning with Residual Weighting Correction
This paper proposes a corrected heavy-ball Q-learning method for reinforcement learning (RL) and establishes its convergence. It also identifies conditions unde…
Sculpting NeRF Geometry: Human-Preference Fine-Tuning of a 3D-Aware Face GAN
Reinforcement learning from human feedback (RLHF) for 3D generation is now established across a number of works, but most existing pipelines optimise explicit s…
Learning the ARTS of Search for Automated Discovery
Scientific discovery can be formulated as an iterative search process over the space of hypotheses and experiments. Contemporary methods navigate this space usi…
Channel Location Constrains the Auditability of Subliminal Learning
Subliminal learning lets a student inherit a teacher's hidden trait from distillation data that never names it. We ask when such transfer can be audited before …
BAC-JEPA: Label-Efficient Breast Arterial Calcification Segmentation via Synthetic Mammography-Guided Supervision
Breast arterial calcification (BAC) on screening mammograms is an emerging cardiovascular risk biomarker, but quantitative use requires reproducible segmentatio…
Residue-Level Attributions in Protein Language Models Do Not Recover Allergen Epitopes
Deep allergenicity classifiers are increasingly used in safety screening of novel foods, and recent protein language models have substantially improved protein-…
When Is Emergent Consensus Real? A Measured Coupling Gain and a Validity Diagnostic for LLM Agent Societies
LLM "agent societies" are studied via demonstrations of emergent consensus or polarization -- with no measurable control parameter, no theory of when each regim…
Variance-Tilted Diffusion Models for Diverse Sampling
Diffusion models are typically sampled independently, even when the downstream objective is to obtain a diverse set of candidates. We introduce a variance-weigh…
Null-Calibrated Conformal Selection via Target-Membership Scores
Conformal selection aims to identify test candidates whose unknown responses fall in a target region while controlling the false discovery rate. Existing method…
Select-to-Act: Hierarchical Reinforcement Learning via Adaptive Language Guidance
Reinforcement Learning (RL) has been widely applied to sequential decision-making, yet it often suffers from poor sample efficiency due to costly interactions w…
ZeroGVC: Zero-Shot Generative Video Compression with Autoregressive Diffusion Priors
Recent generative video compression methods leverage powerful generative priors to achieve perceptually pleasing reconstructions. However, most existing approac…
Grounded Scaling: Why Agentic AI Needs Deterministic Environments
Long-chain agent execution fails exponentially in environments designed for human tolerance: with per-step determinism $δ< 1$, $k$-step chain success degrades a…
From CVE to CWE: Syscall-Based HIDS Generalisation
Host intrusion detection systems (HIDS) based on system-call traces are typically trained and evaluated against individual Common Vulnerabilities and Exposures …