Info Theory
Coding theory, channel capacity, and data compression
20 papers indexed
Secure Rate-Distortion-Perception: A Randomized Distributed Function Computation Approach for Realism
The paper characterizes the secure rate-distortion-perception (RDP) trade-off region for neural image compression over various noisy and noiseless channels, demonstrating that randomized distributed f…
AI Sovereignty as National Learning Capacity: A Human-Centered Learning Mechanics Viewpoint on France, the United States, and China
The paper proposes viewing national AI development, specifically in France, as a 'national AI learning system' governed by a controlled balance between information injection and entropy dissipation, a…
STaR-KV: Spatio-Temporal Adaptive Re-weighting for KV Cache Compression in GUI Vision-Language Models
Yuhang Han, Wenzheng Yang, Yujie Chen, Xiangqi Jin +3 more
STaR-KV introduces a novel, training-free KV cache compression framework that adaptively re-weights token importance across spatial, temporal, and distributional axes, significantly reducing GPU memor…
The Security Budget of Code LLMs: An Information-Theoretic Capacity-Security Bound
The paper establishes an information-theoretic upper bound on the combined functional capacity and perturbation retention of code LLMs, quantifying the security budget available for code generation.
Efficient Provably Secure Linguistic Steganography via Range Coding
The paper proposes an efficient and provably secure linguistic steganography method using range coding that achieves high embedding capacity and speed, outperforming existing methods.
An Information-Geometric Framework for Stability Analysis of Large Language Models under Entropic Stress
The paper proposes a novel information-geometric framework to analyze LLM stability by integrating task utility, external entropy, and internal structural proxies, showing this composite score improve…
Capability and Robustness Cannot Both Be Free: An Information-Theoretic Bound for Vision-Language-Action Models
The paper establishes a theoretical information-theoretic bound proving that for Vision-Language-Action (VLA) models, capability and robustness cannot both be arbitrarily high, quantifying the trade-o…
Safety, Security, and Cognitive Risks in State-Space Models: A Systematic Threat Analysis with Spectral, Stateful, and Capacity Attacks
This paper provides the first systematic threat analysis of State-Space Models (SSMs) in safety-critical applications, introducing novel attack classes and formal metrics to quantify their security an…
InfoMerge: Information-aware Token Compression for Efficient Video Large Language Models
Xinxin Liu, Shiwei Gan, Xiao Liu, Yafeng Yin +2 more
InfoMerge is a novel, training-free method that significantly compresses visual tokens for Video-LLMs by estimating temporal redundancy and allocating tokens based on content richness, achieving high…
Provably Secure Steganography Based on List Decoding
The paper proposes a provably secure steganography scheme based on list decoding that significantly increases embedding capacity for Large Language Models (LLMs) compared to existing methods.
The Sword, Shield, and Achilles' Heel: Characterizing the Linguistic Inductive Bias of Large Language Models for Spatial Reasoning in Navigation Planning
Xudong Zhang, Jian Yang, Shengkai Wang, Jiangpeng Tian +4 more
The paper proposes a dual-interventional framework to characterize how linguistic structures and contextual cues influence LLMs' spatial reasoning for navigation, finding that topological information…
An Application-Layer Multi-Modal Covert-Channel Reference Monitor for LLM Agent Egress
The paper proposes a comprehensive application-layer reference monitor to detect and mitigate data exfiltration via covert channels embedded in LLM agent egress payloads across text, image, and audio…
No More K-means: Single-Stage Sparse Coding for Efficient Multi-Vector Retrieval
Lixuan Guo, Yifei Wang, Tiansheng Wen, Aosong Feng +2 more
The paper introduces Single-stage Sparse Retrieval (SSR), a method that replaces computationally expensive vector clustering with sparse autoencoding to achieve highly efficient multi-vector retrieval…
Simple Power Analysis on Post-Quantum Code Based Cryptosystems
This paper demonstrates that Simple Power Analysis (SPA) can successfully extract secret session key bits from post-quantum cryptosystems, specifically during the key decapsulation phase, using only a…
Toward Covert Quantum Computing
The paper introduces covert quantum computing, a framework to ensure privacy in multi-tenant quantum cloud environments, and finds that while local crosstalk is limited, long-range coupling effects cr…
ACF: A Collaborative Framework for Agent Covert Communication under Cognitive Asymmetry
Wansheng Wu, Kaibo Huang, Yukun Wei, Zhongliang Yang +1 more
The paper introduces the Asymmetric Collaborative Framework (ACF), a novel method that enables robust covert communication between autonomous agents despite inherent cognitive asymmetry caused by dyna…
Rotation-Invariant Spherical Watermarking via Third-Order SO(3) Representation Coupling
Pengzhen Chen, Yanwei Liu, Xiaoyan Gu, Antonios Argyriou +2 more
The paper introduces a novel third-order, rotation-invariant spherical bispectrum for watermarking panoramic images, enabling reliable watermark embedding and extraction under arbitrary 3D rotations.
MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery
Shangheng Du, Xiangchao Yan, Jinxin Shi, Zongsheng Cao +10 more
MLEvolve is a novel self-evolving multi-agent framework that enables LLM agents to discover and optimize machine learning algorithms for complex, long-horizon tasks.
Score Broadcast and Decorrelation: A General Framework for Broadcast-Based Credit Assignment
The paper introduces Score Broadcast and Decorrelation (SBD), a general theoretical framework that unifies broadcast-based credit assignment across various differentiable loss functions by leveraging…
ReSAE: Residualized Sparse Autoencoders for Multi-Layer Transformer Interventions
The paper introduces Residualized Sparse Autoencoders (ReSAEs) to improve multi-layer interventions in transformers by training each layer on the residual activation, which better preserves cross-laye…