All Practice Areas

Immigration Law

이민법

Jurisdiction: All US KR EU Intl
LOW Academic International

Attention Editing: A Versatile Framework for Cross-Architecture Attention Conversion

arXiv:2604.05688v1 Announce Type: new Abstract: Key-Value (KV) cache memory and bandwidth increasingly dominate large language model inference cost in long-context and long-generation regimes. Architectures such as multi-head latent attention (MLA) and hybrid sliding-window attention (SWA) can alleviate this bound, but...

1 min 1 week, 3 days ago
ead
LOW Academic International

Don't Act Blindly: Robust GUI Automation via Action-Effect Verification and Self-Correction

arXiv:2604.05477v1 Announce Type: new Abstract: Autonomous GUI agents based on vision-language models (VLMs) often assume deterministic environment responses, generating actions without verifying whether previous operations succeeded. In real-world settings with network latency, rendering delays, and system interruptions, this assumption leads...

1 min 1 week, 3 days ago
ead
LOW Academic United States

Stop Fixating on Prompts: Reasoning Hijacking and Constraint Tightening for Red-Teaming LLM Agents

arXiv:2604.05549v1 Announce Type: new Abstract: With the widespread application of LLM-based agents across various domains, their complexity has introduced new security threats. Existing red-team methods mostly rely on modifying user prompts, which lack adaptability to new data and may impact...

1 min 1 week, 3 days ago
ead
LOW Academic International

IntentScore: Intent-Conditioned Action Evaluation for Computer-Use Agents

arXiv:2604.05157v1 Announce Type: new Abstract: Computer-Use Agents (CUAs) leverage large language models to execute GUI operations on desktop environments, yet they generate actions without evaluating action quality, leading to irreversible errors that cascade through subsequent steps. We propose IntentScore, a...

1 min 1 week, 3 days ago
ead
LOW Academic International

Efficient Inference for Large Vision-Language Models: Bottlenecks, Techniques, and Prospects

arXiv:2604.05546v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) enable sophisticated reasoning over images and videos, yet their inference is hindered by a systemic efficiency barrier known as visual token dominance. This overhead is driven by a multi-regime interplay between...

1 min 1 week, 3 days ago
ead
LOW Academic International

Do Domain-specific Experts exist in MoE-based LLMs?

arXiv:2604.05267v1 Announce Type: new Abstract: In the era of Large Language Models (LLMs), the Mixture of Experts (MoE) architecture has emerged as an effective approach for training extremely large models with improved computational efficiency. This success builds upon extensive prior...

1 min 1 week, 3 days ago
tps
LOW Academic International

ActivityEditor: Learning to Synthesize Physically Valid Human Mobility

arXiv:2604.05529v1 Announce Type: new Abstract: Human mobility modeling is indispensable for diverse urban applications. However, existing data-driven methods often suffer from data scarcity, limiting their applicability in regions where historical trajectories are unavailable or restricted. To bridge this gap, we...

1 min 1 week, 3 days ago
tps
LOW Academic International

TFRBench: A Reasoning Benchmark for Evaluating Forecasting Systems

arXiv:2604.05364v1 Announce Type: new Abstract: We introduce TFRBench, the first benchmark designed to evaluate the reasoning capabilities of forecasting systems. Traditionally, time-series forecasting has been evaluated solely on numerical accuracy, treating foundation models as ``black boxes.'' Unlike existing benchmarks, TFRBench...

1 min 1 week, 3 days ago
tps
LOW Academic International

LatentAudit: Real-Time White-Box Faithfulness Monitoring for Retrieval-Augmented Generation with Verifiable Deployment

arXiv:2604.05358v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) mitigates hallucination but does not eliminate it: a deployed system must still decide, at inference time, whether its answer is actually supported by the retrieved evidence. We introduce LatentAudit, a white-box auditor...

1 min 1 week, 3 days ago
ead
LOW Academic International

Adaptive Serverless Resource Management via Slot-Survival Prediction and Event-Driven Lifecycle Control

arXiv:2604.05465v1 Announce Type: new Abstract: Serverless computing eliminates infrastructure management overhead but introduces significant challenges regarding cold start latency and resource utilization. Traditional static resource allocation often leads to inefficiencies under variable workloads, resulting in performance degradation or excessive costs....

1 min 1 week, 3 days ago
ead
LOW Academic International

XMark: Reliable Multi-Bit Watermarking for LLM-Generated Texts

arXiv:2604.05242v1 Announce Type: new Abstract: Multi-bit watermarking has emerged as a promising solution for embedding imperceptible binary messages into Large Language Model (LLM)-generated text, enabling reliable attribution and tracing of malicious usage of LLMs. Despite recent progress, existing methods still...

1 min 1 week, 3 days ago
tps
LOW Academic International

PaperOrchestra: A Multi-Agent Framework for Automated AI Research Paper Writing

arXiv:2604.05018v1 Announce Type: new Abstract: Synthesizing unstructured research materials into manuscripts is an essential yet under-explored challenge in AI-driven scientific discovery. Existing autonomous writers are rigidly coupled to specific experimental pipelines, and produce superficial literature reviews. We introduce PaperOrchestra, a...

1 min 1 week, 3 days ago
ead
LOW News United States

The 14th Amendment’s citizenship clause is not trapped in amber: a reflection on oral argument

While I have written multiple posts for SCOTUSblog on birthright citizenship, a substantial part of my practice is litigating Second Amendment claims. In light of that experience, I was struck […]The postThe 14th Amendment’s citizenship clause is not trapped in...

1 min 1 week, 3 days ago
citizenship
LOW News United States

SCOTUStoday for Tuesday, April 7

President Donald Trump is not done complaining about the Supreme Court’s tariffs ruling. Keep reading to learn more about his latest message for the justices.The postSCOTUStoday for Tuesday, April 7appeared first onSCOTUSblog.

1 min 1 week, 3 days ago
ead
LOW Law Review United States

The Higher Education Accommodation Mistake

1 min 1 week, 3 days ago
ead
LOW Law Review United States

Made in the U.S.A.: The Constitutional Crisis Behind America’s Arms Export Regime

3 min 1 week, 3 days ago
ead
LOW Law Review International

First Ideas

2 min 1 week, 3 days ago
ead
LOW Academic International

Regime-Calibrated Demand Priors for Ride-Hailing Fleet Dispatch and Repositioning

arXiv:2604.03883v1 Announce Type: new Abstract: Effective ride-hailing dispatch requires anticipating demand patterns that vary substantially across time-of-day, day-of-week, season, and special events. We propose a regime-calibrated approach that (i) segments historical trip data into demand regimes, (ii) matches the current...

1 min 1 week, 4 days ago
tps
LOW Academic United States

CountsDiff: A Diffusion Model on the Natural Numbers for Generation and Imputation of Count-Based Data

arXiv:2604.03779v1 Announce Type: new Abstract: Diffusion models have excelled at generative tasks for both continuous and token-based domains, but their application to discrete ordinal data remains underdeveloped. We present CountsDiff, a diffusion framework designed to natively model distributions on the...

1 min 1 week, 4 days ago
ead
LOW Academic International

Automated Attention Pattern Discovery at Scale in Large Language Models

arXiv:2604.03764v1 Announce Type: new Abstract: Large language models have found success by scaling up capabilities to work in general settings. The same can unfortunately not be said for interpretability methods. The current trend in mechanistic interpretability is to provide precise...

1 min 1 week, 4 days ago
ead
LOW Academic United States

Algebraic Diversity: Group-Theoretic Spectral Estimation from Single Observations

arXiv:2604.03634v1 Announce Type: new Abstract: We prove that temporal averaging over multiple observations can be replaced by algebraic group action on a single observation for second-order statistical estimation. A General Replacement Theorem establishes conditions under which a group-averaged estimator from...

1 min 1 week, 4 days ago
ead
LOW Academic United States

Readable Minds: Emergent Theory-of-Mind-Like Behavior in LLM Poker Agents

arXiv:2604.04157v1 Announce Type: new Abstract: Theory of Mind (ToM) -- the ability to model others' mental states -- is fundamental to human social cognition. Whether large language models (LLMs) can develop ToM has been tested exclusively through static vignettes, leaving...

1 min 1 week, 4 days ago
ead
LOW Academic United States

Solar-VLM: Multimodal Vision-Language Models for Augmented Solar Power Forecasting

arXiv:2604.04145v1 Announce Type: new Abstract: Photovoltaic (PV) power forecasting plays a critical role in power system dispatch and market participation. Because PV generation is highly sensitive to weather conditions and cloud motion, accurate forecasting requires effective modeling of complex spatiotemporal...

1 min 1 week, 4 days ago
tps
LOW Academic International

Towards the AI Historian: Agentic Information Extraction from Primary Sources

arXiv:2604.03553v1 Announce Type: new Abstract: AI is supporting, accelerating, and automating scientific discovery across a diverse set of fields. However, AI adoption in historical research remains limited due to the lack of solutions designed for historians. In this technical progress...

1 min 1 week, 4 days ago
ead
LOW Academic International

POEMetric: The Last Stanza of Humanity

arXiv:2604.03695v1 Announce Type: new Abstract: Large Language Models (LLMs) can compose poetry, but how far are they from human poets? In this paper, we introduce POEMetric, the first comprehensive framework for poetry evaluation, examining 1) basic instruction-following abilities in generating...

1 min 1 week, 4 days ago
tps
LOW Academic International

TableVision: A Large-Scale Benchmark for Spatially Grounded Reasoning over Complex Hierarchical Tables

arXiv:2604.03660v1 Announce Type: new Abstract: Structured tables are essential for conveying high-density information in professional domains such as finance, healthcare, and scientific research. Despite the progress in Multimodal Large Language Models (MLLMs), reasoning performance remains limited for complex tables with...

1 min 1 week, 4 days ago
ead
LOW Academic International

Structured Multi-Criteria Evaluation of Large Language Models with Fuzzy Analytic Hierarchy Process and DualJudge

arXiv:2604.03742v1 Announce Type: new Abstract: Effective evaluation of large language models (LLMs) remains a critical bottleneck, as conventional direct scoring often yields inconsistent and opaque judgments. In this work, we adapt the Analytic Hierarchy Process (AHP) to LLM-based evaluation and,...

1 min 1 week, 4 days ago
tps
LOW Academic European Union

LangFIR: Discovering Sparse Language-Specific Features from Monolingual Data for Language Steering

arXiv:2604.03532v1 Announce Type: new Abstract: Large language models (LLMs) show strong multilingual capabilities, yet reliably controlling the language of their outputs remains difficult. Representation-level steering addresses this by adding language-specific vectors to model activations at inference time, but identifying language-specific...

1 min 1 week, 4 days ago
tps
LOW Academic International

MetaSAEs: Joint Training with a Decomposability Penalty Produces More Atomic Sparse Autoencoder Latents

arXiv:2604.03436v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) are increasingly used for safety-relevant applications including alignment detection and model steering. These use cases require SAE latents to be as atomic as possible. Each latent should represent a single coherent concept...

1 min 1 week, 4 days ago
ead
LOW Academic International

SODA: Semi On-Policy Black-Box Distillation for Large Language Models

arXiv:2604.03873v1 Announce Type: new Abstract: Black-box knowledge distillation for large language models presents a strict trade-off. Simple off-policy methods (e.g., sequence-level knowledge distillation) struggle to correct the student's inherent errors. Fully on-policy methods (e.g., Generative Adversarial Distillation) solve this via...

1 min 1 week, 4 days ago
ead
Previous Page 11 of 71 Next

Impact Distribution

Critical 0
High 0
Medium 7
Low 2110