All Practice Areas

Arbitration

중재

Jurisdiction: All US KR EU Intl
LOW Academic United States

Emergent Inference-Time Semantic Contamination via In-Context Priming

arXiv:2604.04043v1 Announce Type: new Abstract: Recent work has shown that fine-tuning large language models (LLMs) on insecure code or culturally loaded numeric codes can induce emergent misalignment, causing models to produce harmful content in unrelated downstream tasks. The authors of...

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

To Throw a Stone with Six Birds: On Agents and Agenthood

arXiv:2604.03239v1 Announce Type: new Abstract: Six Birds Theory (SBT) treats macroscopic objects as induced closures rather than primitives. Empirical discussions of agency often conflate persistence (being an object) with control (making a counterfactual difference), which makes agency claims difficult to...

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

Collapse-Free Prototype Readout Layer for Transformer Encoders

arXiv:2604.03850v1 Announce Type: new Abstract: DDCL-Attention is a prototype-based readout layer for transformer encoders that replaces simple pooling methods, such as mean pooling or class tokens, with a learned compression mechanism. It uses a small set of global prototype vectors...

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

NativeTernary: A Self-Delimiting Binary Encoding with Unary Run-Length Hierarchy Markers for Ternary Neural Network Weights, Structured Data, and General Computing Infrastructure

arXiv:2604.03336v1 Announce Type: new Abstract: BitNet b1.58 (Ma et al., 2024) demonstrates that large language models can operate entirely on ternary weights {-1, 0, +1}, yet no native binary wire format exists for such models. NativeTernary closes this gap. We...

1 min 1 week, 3 days ago
bit
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, 3 days ago
adr
LOW News United States

SCOTUStoday for Monday, April 6

On this day in 1938, the Supreme Court heard argument in United States v. Carolene Products, on a law that prohibited interstate shipping of filled milk, an alternative to traditional […]The postSCOTUStoday for Monday, April 6appeared first onSCOTUSblog.

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

Position: Science of AI Evaluation Requires Item-level Benchmark Data

arXiv:2604.03244v1 Announce Type: new Abstract: AI evaluations have become the primary evidence for deploying generative AI systems across high-stakes domains. However, current evaluation paradigms often exhibit systemic validity failures. These issues, ranging from unjustified design choices to misaligned metrics, remain...

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

Social Meaning in Large Language Models: Structure, Magnitude, and Pragmatic Prompting

arXiv:2604.02512v1 Announce Type: new Abstract: Large language models (LLMs) increasingly exhibit human-like patterns of pragmatic and social reasoning. This paper addresses two related questions: do LLMs approximate human social meaning not only qualitatively but also quantitatively, and can prompting strategies...

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

Ambig-IaC: Multi-level Disambiguation for Interactive Cloud Infrastructure-as-Code Synthesis

arXiv:2604.02382v1 Announce Type: cross Abstract: The scale and complexity of modern cloud infrastructure have made Infrastructure-as-Code (IaC) essential for managing deployments. While large Language models (LLMs) are increasingly being used to generate IaC configurations from natural language, user requests are...

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

Mitigating LLM biases toward spurious social contexts using direct preference optimization

arXiv:2604.02585v1 Announce Type: new Abstract: LLMs are increasingly used for high-stakes decision-making, yet their sensitivity to spurious contextual information can introduce harmful biases. This is a critical concern when models are deployed for tasks like evaluating teachers' instructional quality, where...

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

StoryScope: Investigating idiosyncrasies in AI fiction

arXiv:2604.03136v1 Announce Type: new Abstract: As AI-generated fiction becomes increasingly prevalent, questions of authorship and originality are becoming central to how written work is evaluated. While most existing work in this space focuses on identifying surface-level signatures of AI writing,...

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

On the Geometric Structure of Layer Updates in Deep Language Models

arXiv:2604.02459v1 Announce Type: new Abstract: We study the geometric structure of layer updates in deep language models. Rather than analyzing what information is encoded in intermediate representations, we ask how representations change from one layer to the next. We show...

1 min 1 week, 4 days ago
bit
LOW Conference United States

A Retrospective on the ICLR 2026 Review Process

5 min 2 weeks ago
enforcement
LOW Academic United States

Bridging Deep Learning and Integer Linear Programming: A Predictive-to-Prescriptive Framework for Supply Chain Analytics

arXiv:2604.01775v1 Announce Type: new Abstract: Although demand forecasting is a critical component of supply chain planning, actual retail data can exhibit irreconcilable seasonality, irregular spikes, and noise, rendering precise projections nearly unattainable. This paper proposes a three-step analytical framework that...

1 min 2 weeks ago
bit
LOW Academic United States

"Who Am I, and Who Else Is Here?" Behavioral Differentiation Without Role Assignment in Multi-Agent LLM Systems

arXiv:2604.00026v1 Announce Type: new Abstract: When multiple large language models interact in a shared conversation, do they develop differentiated social roles or converge toward uniform behavior? We present a controlled experimental platform that orchestrates simultaneous multi-agent discussions among 7 heterogeneous...

1 min 2 weeks ago
bit
LOW Academic United States

Robust Graph Representation Learning via Adaptive Spectral Contrast

arXiv:2604.01878v1 Announce Type: new Abstract: Spectral graph contrastive learning has emerged as a unified paradigm for handling both homophilic and heterophilic graphs by leveraging high-frequency components. However, we identify a fundamental spectral dilemma: while high-frequency signals are indispensable for encoding...

1 min 2 weeks ago
bit
LOW Academic United States

SECURE: Stable Early Collision Understanding via Robust Embeddings in Autonomous Driving

arXiv:2604.01337v1 Announce Type: new Abstract: While deep learning has significantly advanced accident anticipation, the robustness of these safety-critical systems against real-world perturbations remains a major challenge. We reveal that state-of-the-art models like CRASH, despite their high performance, exhibit significant instability...

1 min 2 weeks ago
bit
LOW Academic United States

More Human, More Efficient: Aligning Annotations with Quantized SLMs

arXiv:2604.00586v1 Announce Type: new Abstract: As Large Language Model (LLM) capabilities advance, the demand for high-quality annotation of exponentially increasing text corpora has outpaced human capacity, leading to the widespread adoption of LLMs in automatic evaluation and annotation. However, proprietary...

1 min 2 weeks ago
bit
LOW News United States

Authors' lucky break in court may help class action over Meta torrenting

Judge gave authors an easier attack on Meta’s torrenting. Meta hopes SCOTUS ruling will block it.

1 min 2 weeks ago
bit
LOW Academic United States

Frege in the Flesh: Biolinguistics and the Neural Enforcement of Syntactic Structures

arXiv:2604.00291v1 Announce Type: new Abstract: Biolinguistics is the interdisciplinary scientific study of the biological foundations, evolution, and genetic basis of human language. It treats language as an innate biological organ or faculty of the mind, rather than a cultural tool,...

1 min 2 weeks ago
enforcement
LOW Academic United States

PI-JEPA: Label-Free Surrogate Pretraining for Coupled Multiphysics Simulation via Operator-Split Latent Prediction

arXiv:2604.01349v1 Announce Type: new Abstract: Reservoir simulation workflows face a fundamental data asymmetry: input parameter fields (geostatistical permeability realizations, porosity distributions) are free to generate in arbitrary quantities, yet existing neural operator surrogates require large corpora of expensive labeled simulation...

1 min 2 weeks ago
bit
LOW Academic United States

Human-in-the-Loop Control of Objective Drift in LLM-Assisted Computer Science Education

arXiv:2604.00281v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly embedded in computer science education through AI-assisted programming tools, yet such workflows often exhibit objective drift, in which locally plausible outputs diverge from stated task specifications. Existing instructional responses...

1 min 2 weeks ago
bit
LOW Think Tank United States

Prominent Scientists, Faith Leaders, Policymakers and Artists Call for a Prohibition on Superintelligence, as Poll Shows Americans Don’t Want It

Initial signatories include AI pioneers Yoshua Bengio and Geoffrey Hinton, leading media voices Steve Bannon and Glenn Beck, Obama's National Security Advisor Susan Rice, business trailblazers Steve Wozniak and Richard Branson, five Nobel Laureates, former Irish President Mary Robinson, actors...

1 min 2 weeks, 5 days ago
bit
LOW Academic United States

Compression Method Matters: Benchmark-Dependent Output Dynamics in LLM Prompt Compression

arXiv:2603.23527v1 Announce Type: new Abstract: Prompt compression is often evaluated by input-token reduction, but its real deployment impact depends on how compression changes output length and total inference cost. We present a controlled replication and extension study of benchmark-dependent output...

1 min 3 weeks, 1 day ago
bit
LOW Academic United States

Why the Maximum Second Derivative of Activations Matters for Adversarial Robustness

arXiv:2603.23860v1 Announce Type: new Abstract: This work investigates the critical role of activation function curvature -- quantified by the maximum second derivative $\max|\sigma''|$ -- in adversarial robustness. Using the Recursive Curvature-Tunable Activation Family (RCT-AF), which enables precise control over curvature...

1 min 3 weeks, 1 day ago
bit
LOW Academic United States

Chain-of-Authorization: Internalizing Authorization into Large Language Models via Reasoning Trajectories

arXiv:2603.22869v1 Announce Type: new Abstract: Large Language Models (LLMs) have become core cognitive components in modern artificial intelligence (AI) systems, combining internal knowledge with external context to perform complex tasks. However, LLMs typically treat all accessible data indiscriminately, lacking inherent...

1 min 3 weeks, 2 days ago
bit
LOW Academic United States

AI Mental Models: Learned Intuition and Deliberation in a Bounded Neural Architecture

arXiv:2603.22561v1 Announce Type: new Abstract: This paper asks whether a bounded neural architecture can exhibit a meaningful division of labor between intuition and deliberation on a classic 64-item syllogistic reasoning benchmark. More broadly, the benchmark is relevant to ongoing debates...

1 min 3 weeks, 2 days ago
bit
LOW Academic United States

Describe-Then-Act: Proactive Agent Steering via Distilled Language-Action World Models

arXiv:2603.23149v1 Announce Type: new Abstract: Deploying safety-critical agents requires anticipating the consequences of actions before they are executed. While world models offer a paradigm for this proactive foresight, current approaches relying on visual simulation incur prohibitive latencies, often exceeding several...

1 min 3 weeks, 2 days ago
bit
LOW Academic United States

DALDALL: Data Augmentation for Lexical and Semantic Diverse in Legal Domain by leveraging LLM-Persona

arXiv:2603.22765v1 Announce Type: new Abstract: Data scarcity remains a persistent challenge in low-resource domains. While existing data augmentation methods leverage the generative capabilities of large language models (LLMs) to produce large volumes of synthetic data, these approaches often prioritize quantity...

1 min 3 weeks, 2 days ago
bit
LOW Academic United States

Beyond Hate: Differentiating Uncivil and Intolerant Speech in Multimodal Content Moderation

arXiv:2603.22985v1 Announce Type: new Abstract: Current multimodal toxicity benchmarks typically use a single binary hatefulness label. This coarse approach conflates two fundamentally different characteristics of expression: tone and content. Drawing on communication science theory, we introduce a fine-grained annotation scheme...

1 min 3 weeks, 2 days ago
bit
Previous Page 2 of 8 Next

Impact Distribution

Critical 0
High 0
Medium 3
Low 912