arXiv AI
Jun 4
PersistBench: When Should Long-Term Memories Be Forgotten by LLMs?
arXiv:2602. 01146v2 Announce Type: replace Abstract: Conversational assistants are increasingly integrating long-term memory with large language models (LLMs).
AI safety and alignment
Alignment, interpretability, red-teaming, bias and privacy: the research on what these systems do when they misbehave.
arXiv AI
Jun 4
OA-CutMix: Correcting the Label Bias of CutMix
arXiv:2606. 04820v1 Announce Type: cross Abstract: CutMix has become the de facto standard mixing augmentation, yet its label assignment rests on a flawed assumption: The area of the pasted patch faithfully reflects its semantic contribution to the mixed image.
arXiv AI
Jun 4
P$^2$-DPO: Grounding Hallucination in Perceptual Processing via Calibration Direct Preference Optimization
arXiv:2606. 03376v2 Announce Type: replace-cross Abstract: Hallucination has recently garnered significant research attention in Large Vision-Language Models (LVLMs).
arXiv Machine Learning
Jun 4
Edge of Stability Selectively Shapes Learning Across the Data Distribution
arXiv:2606. 04212v1 Announce Type: new Abstract: Existing analyses of the edge of stability (EoS) treat it as a global property of optimization.
arXiv AI
Jun 4
Incremental Sheaf Cohomology on Cellular Complexes: O(1)-in-n Lazy Edit Processing under Bounded Local Geometry
arXiv:2606. 04227v1 Announce Type: cross Abstract: We present an algorithmic framework for incremental maintenance of first sheaf cohomology $H^1(X; \mathcal{F})$ on dynamically evolving 1-dimensional cellular complexes equipped with finite-dimensional cellular sheaves.
arXiv AI
Jun 4
MorphoQuant: Modality-Aware Quantization for Omni-modal Large Language Models
arXiv:2606. 04349v1 Announce Type: cross Abstract: Conventional Post-Training Quantization (PTQ) methods struggle with 4-bit Omni-modal Large Language Models (OLLMs) due to the extreme distribution heterogeneity and disparate outlier patterns across modalities.
arXiv Machine Learning
Jun 4
Fixed Aggregation Features Can Rival GNNs
arXiv:2601. 19449v2 Announce Type: replace Abstract: Graph neural networks (GNNs) are widely believed to excel at node representation learning through trainable neighborhood aggregations.
arXiv Machine Learning
Jun 4
Vision Transformer Finetuning Benefits from Non-Smooth Components
arXiv:2602. 06883v3 Announce Type: replace Abstract: The smoothness of the transformer architecture has been extensively studied in the context of generalization, training stability, and adversarial robustness.
arXiv AI
Jun 4
NoRA: Evaluating Grounded Reasonableness in Visual First-person Normative Action Reasoning
arXiv:2606. 04806v1 Announce Type: cross Abstract: LLMs and agentic systems are increasingly deployed in social environments, making normative competence critical for safe and appropriate behavior.
arXiv AI
Jun 4
SharedRequest: Privacy-Preserving Model-Agnostic Inference for Large Language Models
arXiv:2606. 05004v1 Announce Type: cross Abstract: With the widespread deployment of public large language models (LLMs) such as ChatGPT, protecting user prompt privacy has become an increasingly critical issue.
arXiv AI
Jun 4
Retrieval and competition: how a protein foundation model starts a protein
arXiv:2605. 16331v2 Announce Type: replace-cross Abstract: Protein language models are increasingly used to guide experimental and clinical decisions, yet it is often unclear whether a confident prediction reflects recognition of biological evidence or retrieval of a statistical default.
arXiv AI
Jun 4
From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agents
arXiv:2606. 04329v1 Announce Type: cross Abstract: Memory is a core component of AI agents, enabling them to accumulate knowledge across interactions and improve performance.
arXiv AI
Jun 4
TITAN-FedAnil+: Trust-Based Adaptive Blockchain Federated Learning for Resource-Constrained Intelligent Enterprises
arXiv:2606. 04388v1 Announce Type: cross Abstract: Federated Learning (FL) has emerged as an effective paradigm for collaborative intelligence while preserving data privacy.
arXiv AI
Jun 4
What If Prompt Injection Never Left? Exploring Cross-Session Stored Prompt Injection in Agentic Systems
arXiv:2606. 04425v1 Announce Type: cross Abstract: Modern agentic systems transform LLMs from session-bounded assistants into stateful systems that persist and evolve shared world state across sessions through memories, filesystems, tools, and other long-lived contextual artifacts.
arXiv AI
Jun 4
ParetoPilot: Zero-Surrogate Offline Multi-Objective Optimization via Infer-Perturb-Guide Diffusion
arXiv:2606. 04468v1 Announce Type: cross Abstract: Offline multi-objective optimization (Offline MOO) aims to discover novel Pareto-optimal designs based on static datasets without expensive environment interactions.
arXiv AI
Jun 4
SoLoPO: Unlocking Long-Context Capabilities in LLMs via Short-to-Long Preference Optimization
arXiv:2505. 11166v3 Announce Type: replace-cross Abstract: Despite advances in pretraining with extended context sizes, large language models (LLMs) still face challenges in effectively utilizing real-world long-context information, primarily due to insufficient long-context alignment caused by data quality issues, training inefficiencies, and the lack of well-designed optimization objectives.
arXiv AI
Jun 4
Simplicial Embeddings Improve Sample Efficiency in Actor-Critic Agents
arXiv:2510. 13704v2 Announce Type: replace-cross Abstract: Recent works have proposed accelerating the wall-clock training time of actor-critic methods via the use of large-scale environment parallelization; unfortunately, these can sometimes still require large number of environment interactions to achieve a desired level of performance.
arXiv Machine Learning
Jun 4
KODA: Contrastive Representation Comparison and Alignment for Vision-Language Foundation Models
arXiv:2606. 04180v1 Announce Type: new Abstract: Vision-language foundation models such as CLIP and SigLIP provide widely used representations for multimodal learning systems.
arXiv Machine Learning
Jun 4
Measuring Model Robustness via Fisher Information: Spectral Bounds, Theoretical Guarantees, and Practical Algorithms
arXiv:2606. 04767v1 Announce Type: new Abstract: The robustness of deep neural networks is crucial for safety-critical deployments, yet existing evaluation methods are often attack-dependent and lack interpretability.
arXiv Machine Learning
Jun 4
veriFIRE: an Industrial Case Study in Verifying Consistency Properties for a DNN-Based Wildfire Detection System
arXiv:2606. 04121v1 Announce Type: cross Abstract: We present our ongoing work on the veriFIRE project: a collaboration between industry and academia, aimed at applying verification to increase the reliability of a real-world, safety-critical system.