research

BioHiCL: Hierarchical Multi-Label Contrastive Learning for Biomedical Retrieval with MeSH Labels

arXiv:2604.15591v1 Announce Type: cross Abstract: Effective biomedical information retrieval requires modeling domain semantics and hierarchical relationships among biomedical texts. Existing biomedic

Research

Brain Score Tracks Shared Properties of Languages: Evidence from Many Natural Languages and Structured Sequences

DGX agent

arXiv:2604.15503v1 Announce Type: new Abstract: Recent breakthroughs in language models (LMs) using neural networks have raised the question: how similar are these models' processing to human language

researcharxiv-cs-cl

20 Apr 2026

Breakout-picker: Reducing false positives in deep learning-based borehole breakout characterization from acoustic image logs

arXiv:2604.16011v1 Announce Type: new Abstract: Borehole breakouts are stress-induced spalling on the borehole wall, which are identifiable in acoustic image logs as paired zones with near-symmetry az

Bureaucratic Silences: What the Canadian AI Register Reveals, Omits, and Obscures

arXiv:2604.15514v1 Announce Type: new Abstract: In November 2025, the Government of Canada operationalized its commitment to transparency by releasing its first Federal AI Register. In this paper, we

Can LLMs Understand the Impact of Trauma? Costs and Benefits of LLMs Coding the Interviews of Firearm Violence Survivors

arXiv:2604.16132v1 Announce Type: cross Abstract: Firearm violence is a pressing public health issue, yet research into survivors' lived experiences remains underfunded and difficult to scale. Qualita

Can we AI our way to a more sustainable world?

researchmicrosoft-research

Doug Burger, sustainability expert Amy Luers, and optimization researcher Ishai Menache examine the global emissions implications of datacenter operations, efficiency gains, and AI's potential across

Chain-of-Thought Degrades Visual Spatial Reasoning Capabilities of Multimodal LLMs

arXiv:2604.16060v1 Announce Type: cross Abstract: Multimodal Reasoning Models (MRMs) leveraging Chain-of-Thought (CoT) based thinking have revolutionized mathematical and logical problem-solving. Howe

Chinese tech workers are starting to train their AI doubles–and pushing back

Tech workers in China are being instructed by their bosses to train AI agents to replace them—and it’s prompting a wave of soul-searching among otherwise enthusiastic early adopters. Earlier this mont

researchmit-tech-review

CIG: Measuring Conversational Information Gain in Deliberative Dialogues with Semantic Memory Dynamics

arXiv:2604.15647v1 Announce Type: new Abstract: Measuring the quality of public deliberation requires evaluating not only civility or argument structure, but also the informational progress of a conve

CiPO: Counterfactual Unlearning for Large Reasoning Models through Iterative Preference Optimization

arXiv:2604.15847v1 Announce Type: new Abstract: Machine unlearning has gained increasing attention in recent years, as a promising technique to selectively remove unwanted privacy or copyrighted infor

CLewR: Curriculum Learning with Restarts for Machine Translation Preference Learning

arXiv:2601.05858v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have demonstrated competitive performance in zero-shot multilingual machine translation (MT). Some follow-up work

CLIMB: Controllable Longitudinal Brain Image Generation using Mamba-based Latent Diffusion Model and Gaussian-aligned Autoencoder

arXiv:2604.15611v1 Announce Type: cross Abstract: Latent diffusion models have emerged as powerful generative models in medical imaging, enabling the synthesis of high quality brain magnetic resonance

Closing the Theory-Practice Gap in Spiking Transformers via Effective Dimension

arXiv:2604.15769v1 Announce Type: cross Abstract: Spiking transformers achieve competitive accuracy with conventional transformers while offering 38-57imes energy efficiency on neuromorphic hardware,

CLOTH-HUGS: Cloth Aware Human Gaussian Splatting

arXiv:2604.15875v1 Announce Type: new Abstract: We present Cloth-HUGS, a Gaussian Splatting based neural rendering framework for photorealistic clothed human reconstruction that explicitly disentangle

Collaboration of Fusion and Independence: Hypercomplex-driven Robust Multi-Modal Knowledge Graph Completion

arXiv:2509.23714v2 Announce Type: replace Abstract: Multi-modal knowledge graph completion (MMKGC) aims to discover missing facts in multi-modal knowledge graphs (MMKGs) by leveraging both structural

Collaborative Filtering Through Weighted Similarities of User and Item Embeddings

arXiv:2604.15573v1 Announce Type: cross Abstract: In recent years, neural networks and other complex models have dominated recommender systems, often setting new benchmarks for state-of-the-art perfor

Collective Kernel EFT for Pre-activation ResNets

arXiv:2604.15742v1 Announce Type: new Abstract: In finite-width deep neural networks, the empirical kernel G evolves stochastically across layers. We develop a collective kernel effective field theory

CollideNet: Hierarchical Multi-scale Video Representation Learning with Disentanglement for Time-To-Collision Forecasting

arXiv:2604.16240v1 Announce Type: new Abstract: Time-to-Collision (TTC) forecasting is a critical task in collision prevention, requiring precise temporal prediction and comprehending both local and g

Colossal Biosciences said it cloned red wolves. Is it for real?

If you want to capture something wolflike, it’s best to embark before dawn. So on a morning this January, with the eastern horizon still pink-hued, I drove with two young scientists into a blanket of

researchmit-tech-review

Comparison Study: Glacier Calving Front Delineation in Synthetic Aperture Radar Images With Deep Learning

arXiv:2501.05281v2 Announce Type: replace Abstract: Continuous monitoring of glacier calving fronts is essential for sea level rise projections. This study benchmarks Deep Learning systems for front d

ConlangCrafter: Constructing Languages with a Multi-Hop LLM Pipeline

arXiv:2508.06094v4 Announce Type: replace Abstract: Constructed languages (conlangs) such as Esperanto and Quenya have played diverse roles in art, philosophy, and international communication. Meanwhi

Corner Reflector Array Jamming Discrimination Using Multi-Dimensional Micro-Motion Features with Frequency Agile Radar

arXiv:2604.16008v1 Announce Type: new Abstract: This paper introduces a robust discrimination method for distinguishing real ship targets from corner-reflector-array jamming with frequency-agile radar

Cost-Aware Model Orchestration for LLM-based Systems

arXiv:2512.01099v2 Announce Type: replace Abstract: As modern artificial intelligence (AI) systems become more advanced and capable, they can leverage a wide range of tools and models to perform compl

COVER:COverage-VErified Roadmaps for Fixed-time Motion Planning in Continuous Semi-Static Environments

arXiv:2510.03875v2 Announce Type: replace Abstract: The ability to solve motion-planning queries within a fixed time budget is critical for deploying robotic systems in time-sensitive applications. Se

researcharxiv-cs-ro

Creating and Evaluating Personas Using Generative AI: A Scoping Review of 81 Articles

arXiv:2504.04927v2 Announce Type: replace-cross Abstract: As generative AI (GenAI) is increasingly applied in persona development to represent real users, understanding the implications and limitation

CRoCoDiL: Continuous and Robust Conditioned Diffusion for Language

arXiv:2603.20210v3 Announce Type: replace-cross Abstract: Masked Diffusion Models (MDMs) provide an efficient non-causal alternative to autoregressive generation but often struggle with token dependen

Curing Miracle Steps in LLM Mathematical Reasoning with Rubric Rewards

arXiv:2510.07774v3 Announce Type: replace Abstract: In this paper, we observe that current models are susceptible to reward hacking, leading to a substantial overestimation of a model's reasoning abil

Dental Panoramic Radiograph Analysis Using YOLO26 From Tooth Detection to Disease Diagnosis

arXiv:2604.16231v1 Announce Type: new Abstract: Panoramic radiography is a fundamental diagnostic tool in dentistry, offering a comprehensive view of the entire dentition with minimal radiation exposu

Detecting and Suppressing Reward Hacking with Gradient Fingerprints

arXiv:2604.16242v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) typically optimizes for outcome rewards without imposing constraints on intermediate reasoning.

Differential privacy representation geometry for medical image analysis

arXiv:2603.01098v2 Announce Type: replace-cross Abstract: Differential privacy (DP)'s effect in medical imaging is typically evaluated only through end-to-end performance, leaving the mechanism of pri

Disentangling Mathematical Reasoning in LLMs: A Methodological Investigation of Internal Mechanisms

arXiv:2604.15842v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated impressive capabilities, yet their internal mechanisms for handling reasoning-intensive tasks remain unde

Dispatch-Aware Ragged Attention for Pruned Vision Transformers

arXiv:2604.15408v1 Announce Type: cross Abstract: Token pruning methods for Vision Transformers (ViTs) promise quadratic reductions in attention FLOPs by dropping uninformative patches. Yet when prune

Do LLMs Really Know What They Don't Know? Internal States Mainly Reflect Knowledge Recall Rather Than Truthfulness

arXiv:2510.09033v3 Announce Type: replace Abstract: Recent work suggests that LLMs 'know what they don't know', positing that hallucinated and factually correct outputs arise from distinct internal pr

Driving Assistance System for Ambulances to Minimise the Vibrations in Patient Cabin

arXiv:2604.16047v1 Announce Type: cross Abstract: The ambulance service is the main transport for diseased or injured people which suffers the same acceleration forces as regular vehicles. These accel

DTEA: A Dual-Topology Elastic Actuator Enabling Real-Time Switching Between Series and Parallel Compliance

arXiv:2604.15865v1 Announce Type: new Abstract: Series and parallel elastic actuators offer complementary but mutually exclusive advantages, yet no existing actuator enables real-time transition betwe

researcharxiv-cs-ro

DVP-MVS++: Synergize Depth-Normal-Edge and Harmonized Visibility Prior for Multi-View Stereo

arXiv:2506.13215v2 Announce Type: replace Abstract: Recently, patch deformation-based methods have demonstrated significant effectiveness in multi-view stereo due to their incorporation of deformable

Dwarkesh is not an AGI party bro. He's been pretty diverse in how he seeks alpha from across a wide variety of industries. I enjoy the hell …

researchsoumith-chintala--x

Dwarkesh is not an AGI party bro. He's been pretty diverse in how he seeks alpha from across a wide variety of industries. I enjoy the hell out of a lot of his podcasts. This podcast though, his quest

Early Detection of Acute Myeloid Leukemia (AML) Using YOLOv12 Deep Learning Model

arXiv:2604.16082v1 Announce Type: cross Abstract: Acute Myeloid Leukemia (AML) is one of the most life-threatening type of blood cancers, and its accurate classification is considered and remains a ch

EchoVLM: Dynamic Mixture-of-Experts Vision-Language Model for Universal Ultrasound Intelligence

arXiv:2509.14977v2 Announce Type: replace Abstract: Ultrasound imaging has become the preferred imaging modality for early cancer screening due to its advantages of non-ionizing radiation, low cost, a

EDINET-Bench: Evaluating LLMs on Complex Financial Tasks using Japanese Financial Statements https://arxiv.org/abs/2506.08762 https://sakana…

EDINET-Bench is a benchmark dataset that evaluates large language models on complex financial analysis tasks using Japanese financial statements from the EDINET database. The benchmark tests LLM capab

researchdavid-ha--x

Enhancing Hazy Wildlife Imagery: AnimalHaze3k and IncepDehazeGan

arXiv:2604.16284v1 Announce Type: new Abstract: Atmospheric haze significantly degrades wildlife imagery, impeding computer vision applications critical for conservation, such as animal detection, tra

Environment-Adaptive Solid-State LiDAR-Inertial Odometry

arXiv:2604.15864v1 Announce Type: new Abstract: Solid-state LiDAR-inertial SLAM has attracted significant attention due to its advantages in speed and robustness. However, achieving accurate mapping i

researcharxiv-cs-ro

Evaluating LLMs as Human Surrogates in Controlled Experiments

arXiv:2604.15329v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to simulate human responses in behavioral research, yet it remains unclear when LLM-generated data

Evaluating quality in synthetic data generation for large tabular health datasets

arXiv:2604.15961v1 Announce Type: new Abstract: There is no consensus in the field of synthetic data on concise metrics for quality evaluations or benchmarks on large health datasets, such as historic

EventCrab: Harnessing Frame and Point Synergy for Event-based Action Recognition and Beyond

arXiv:2411.18328v2 Announce Type: replace Abstract: Event-based Action Recognition (EAR) possesses the advantages of high-temporal resolution capturing and privacy preservation compared with tradition

EVIL: Evolving Interpretable Algorithms for Zero-Shot Inference on Event Sequences and Time Series with LLMs

arXiv:2604.15787v1 Announce Type: cross Abstract: We introduce EVIL (extbf{EV}olving extbf{I}nterpretable algorithms with extbf{L}LMs), an approach that uses LLM-guided evolutionary search to discover

Examining the Relationship between Scientific Publishing Activity and Hype-Driven Financial Bubbles: A Comparison of the Dot-Com and AI Eras

arXiv:2509.11982v2 Announce Type: replace Abstract: Financial bubbles often arrive without much warning, but create long-lasting economic effects. For example, during the dot-com bubble, innovative te

Exascale Multi-Task Graph Foundation Models for Imbalanced, Multi-Fidelity Atomistic Data

arXiv:2604.15380v1 Announce Type: cross Abstract: We present an exascale workflow for materials discovery using atomistic graph foundation models built on HydraGNN. We jointly train on 16 open first-p