arXiv:2604.14495v1 Announce Type: cross Abstract: Financial institutions face tension between maximizing data utility and mitigating the re-identification risks inherent in traditional anonymization methods. This paper explores Differentially Private (DP) synthetic data as a robust “Privacy by Design” framework to resolve this conflict, ensuring output privacy while satisfying stringent regulatory obligations. We examine two distinct generative […]
CogEvolution: A Human-like Generative Educational Agent to Simulate Student’s Cognitive Evolution
arXiv:2604.14786v1 Announce Type: new Abstract: Generative Agents, owing to their precise modeling and simulation capabilities of human behavior, have become a pivotal tool in the field of Artificial Intelligence in Education (AIEd) for uncovering complex cognitive processes of learners. However, existing educational agents predominantly rely on static personas to simulate student learning behaviors, neglecting the […]
XMark: Reliable Multi-Bit Watermarking for LLM-Generated Texts
arXiv:2604.05242v2 Announce Type: replace-cross 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 face key limitations: some become computationally infeasible for large messages, while others suffer from a […]
PUFFIN: Protein Unit Discovery with Functional Supervision
arXiv:2604.14796v1 Announce Type: new Abstract: Proteins carry out biological functions through the coordinated action of groups of residues organized into structural arrangements. These arrangements, which we refer to as protein units, exist at an intermediate scale, being larger than individual residues yet smaller than entire proteins. A deeper understanding of protein function can be achieved […]
A Nonasymptotic Theory of Gain-Dependent Error Dynamics in Behavior Cloning
arXiv:2604.14484v1 Announce Type: cross Abstract: Behavior cloning (BC) policies on position-controlled robots inherit the closed-loop response of the underlying PD controller, yet the effect of controller gains on BC failure lacks a nonasymptotic theory. We show that independent sub-Gaussian action errors propagate through the gain-dependent closed-loop dynamics to yield sub-Gaussian position errors whose proxy matrix […]
TrigReason: Trigger-Based Collaboration between Small and Large Reasoning Models
arXiv:2604.14847v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) achieve strong performance on complex tasks through extended chains of thought but suffer from high inference latency due to autoregressive reasoning. Recent work explores using Small Reasoning Models (SRMs) to accelerate LRM inference. In this paper, we systematically characterize the capability boundaries of SRMs and identify […]
Counting Without Numbers and Finding Without Words
arXiv:2603.24470v2 Announce Type: replace-cross Abstract: Every year, 10 million pets enter shelters, separated from their families. Despite desperate searches by both guardians and lost animals, 70% never reunite, not because matches do not exist, but because current systems look only at appearance, while animals recognize each other through sound. We ask, why does computer vision […]
MemoSight: Unifying Context Compression and Multi Token Prediction for Reasoning Acceleration
arXiv:2604.14889v1 Announce Type: new Abstract: While Chain-of-thought (CoT) reasoning enables LLMs to solve challenging reasoning problems, as KV cache grows linearly with the number of generated tokens, CoT reasoning faces scaling issues in terms of speed and memory usage. In this work, we propose MemoSight (Memory-Foresight-based reasoning), a unified framework that integrates both context compression […]
Auxiliary Finite-Difference Residual-Gradient Regularization for PINNs
arXiv:2604.14472v1 Announce Type: cross Abstract: Physics-informed neural networks (PINNs) are often selected by a single scalar loss even when the quantity of interest is more specific. We study a hybrid design in which the governing PDE residual remains automatic-differentiation (AD) based, while finite differences (FD) appear only in a weak auxiliary term that penalizes gradients […]
Dual-Axis Generative Reward Model Toward Semantic and Turn-taking Robustness in Interactive Spoken Dialogue Models
arXiv:2604.14920v1 Announce Type: new Abstract: Achieving seamless, human-like interaction remains a key challenge for full-duplex spoken dialogue models (SDMs). Reinforcement learning (RL) has substantially enhanced text- and vision-language models, while well-designed reward signals are crucial for the performance of RL. We consider RL a promising strategy to address the key challenge for SDMs. However, a […]
Unilateral Relationship Revision Power in Human-AI Companion Interaction
arXiv:2603.23315v4 Announce Type: replace-cross Abstract: When providers update AI companions, users report grief, betrayal, and loss. A growing literature asks whether the norms governing personal relationships extend to these interactions. So what, if anything, is morally significant about them? I argue that this debate has missed a prior structural question: who controls the relationship, and […]
TRACER: Trace-Based Adaptive Cost-Efficient Routing for LLM Classification
arXiv:2604.14531v1 Announce Type: new Abstract: Every call to an LLM classification endpoint produces a labeled input-output pair already retained in production logs. These pairs constitute a free, growing training set: a lightweight surrogate trained on them can absorb a significant portion of future traffic at near-zero marginal inference cost. The open questions are when the […]