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 stories
Farewell Ai2
This was my last week at the Allen Institute for AI (Ai2), where I got the great privilege to work on the Olmo models, to grow, to learn, and to have broad last…
Import AI 460: Reward hacking society, RSI data from Anthropic; and RL-based quadcopter racing
When will markets price the singularity?…
Claude Fable 5 and new AI safety fables
One step further into the power politics of frontier AI systems.…
Agentic MPC for Semantic Control System Resynthesis
While MPC effectively handles structured, diverse, and low-level specifications, it lacks the capability to dynamically incorporate high-level contextual inform…
SymQNet: Amortized Acquisition for Low-Latency Adaptive Hamiltonian Learning
Adaptive Hamiltonian learning is central to calibrating and characterizing quantum devices. In an adaptive controller, choosing the next experiment is itself a …
Graph Reinforcement Learning for Calibration-Aware Quantum Circuit Routing
Quantum circuit routing is a key step in compiling programs for noisy intermediate-scale quantum processors. Routes that appear efficient by standard overhead m…
CLARITree: Cholesky and Lookahead Accelerations for Regression with Interpretable Piecewise Linear Trees
Regression trees are among the most interpretable yet expressive model classes in machine learning. Historically, greedy induction has been the dominant approac…
Interpretable Factor Decomposition for Decision Intelligence in Large-Scale Financial Markets: Evidence from China's A-Share Market
We present an interpretable machine learning pipeline to decompose Cross-Sectional Equity Return Predictability into auditable factor contribution. We apply an …
The Hidden Power of Scaling Factor in LoRA Optimization
In Low-Rank Adaptation (LoRA), the scaling factor $α$ is often treated as a mere complement to the learning rate, yet its role in optimization remains poorly un…
Bridging Modal Isolation in Interleaved Thinking: Supervising Modality Transitions via Stepwise Reinforcement
Interleaved thinking, where a unified multimodal model alternates between textual reasoning and visual generation, has shown promise on spatial and physical tas…
LongSpike: Fractional Order Spiking State Space Models for Efficient Long Sequence Learning
Spiking Neural Networks (SNNs) are well-regarded for their biological plausibility and energy efficiency in processing sequential data. However, dominant SNN ar…
Multi-Label Test-Time Adaptation with Bayesian Conditional Priors
Multi-label recognition with frozen Vision-Language Models (VLMs) is brittle under distribution shift: standard zero-shot inference scores labels independently,…
MARS: Margin-Adversarial Risk-controlled Stopping for Parallel LLM Test-time Scaling
Parallel test-time scaling samples many reasoning traces and majority-votes their answers, improving LLM accuracy but requiring traces to run to completion, inc…
PRISMR: Overcoming Parse Collapse in Multimodal Listwise Ranking via Parameterized Representation Internalization
Generative listwise ranking with Large Multimodal Models (LMMs) aims to capture global list context in a single forward pass, but its effectiveness degrades in …
Circuit Synchronization Precedes Generalization: Causal Evidence from Fourier Structure in Grokking Transformers
Grokking -- where a transformer on modular arithmetic suddenly transitions from near-chance to near-perfect validation accuracy -- is attributed to a Fourier ci…
Quality-Preserving Imperceptible Adversarial Attack on Skeleton-based Human Action Recognition
Adversarial attacks on skeletal human action recognition have received significant attention. However, existing methods typically introduce noise-like perturbat…
TetherCache: Stabilizing Autoregressive Long-Form Video Generation with Gated Recall and Trusted Alignment
Autoregressive video diffusion models provide a natural formulation for streaming and variable-length video generation by conditioning newly generated frames on…
TWLA: Achieving Ternary Weights and Low-Bit Activations for LLMs via Post-Training Quantization
Large language models (LLMs) exhibit exceptional general language processing capabilities, but their memory and compute costs hinder deployment. Ternarization h…
Limits of spectral learning under noise
Learning functional relationships from noisy data is a central problem in scientific inference. Spectral methods approximate unknown functions by expanding them…
Authority, Truth, and Citation Bias: A Large-Scale Multi-Domain Benchmark for Studying Epistemic Susceptibility in Large Language Models
Large language models are increasingly deployed in citation-augmented settings, yet the effect of citation presence on model behavior independent of factual con…
Disparate Impact in Synthetic Data Generation
We revisit the fairness notion of disparate impact for synthetic data generation (SDG), that assesses whether the utility of generated records is the same acros…
MiniPIC: Flexible Position-Independent Caching in <100LOC
Retrieval-augmented and agentic workloads repeatedly prefill recurring predictable structured inputs (which we call "spans") such as documents and code files. Y…
Learning-Augmented Approximation for Unrelated-Machines Makespan Scheduling
Recently, Antoniadis et al. (ICLR 2025) proposed a framework for incorporating predictions to approximate NP-hard selection problems. Despite its simplicity, th…
MemRefine: LLM-Guided Compression for Long-Term Agent Memory
Large language model (LLM) agents are increasingly expected to operate over long-term interactions, where information from past dialogues must be preserved and …
Modern analog computing for solving differential and matrix equations
In recent years, driven by the computational demands of data-intensive applications such as artificial intelligence and scientific computing, analog computing h…
Layer-Resolved Optimal Transport for Hallucination Detection in NMT and Abstractive Summarization
Optimal transport (OT) has been shown to detect hallucinations in neural machine translation (NMT) by measuring the geometric distance between cross-attention d…
LLM-as-an-Investigator: Evidence-First Reasoning for Robust Interactive Problem Diagnosis
Large language models (LLMs) are increasingly used as interactive assistants for technical problem solving. However, when users provide incomplete descriptions …
Distributional Loss for Robust Classification
This paper proposes a novel loss concept for supervised classification tasks. Rather than enforcing a direct mapping from each input sample to a single assigned…
Different Layers, Different Manifolds: Module-Wise Weight-Space Geometry in Transformer Optimization
Weight-space geometry plays a central role in neural network optimization, yet manifold constraints are often applied uniformly across all weight matrices. In t…
Once-for-All: Scalable Simultaneous Forecasting via Equilibrium State Estimation
We introduce Equilibrium State Estimation (ESE), a novel paradigm for simultaneous prediction, where multiple interacting systems require separate yet coordinat…