In regulated industries like consumer finance, seemingly harmless user queries can exploit large language model vulnerabilities, triggering safety failures and pushing responses dangerously close to policy limits. Existing automated red-teaming methods trade off attack effectiveness against generation cost, while treat...
Rikhiya Ghosh, Himanshu Kumar, Sriram Venkatapathy et al.· 0 citations
Inspired by the recent success of Byte Latent Transformer, DP-Rec is proposed, a dynamic latent patching architecture for recommendation that scales effectively to long sequences and achieves a superior efficiency–accuracy trade-off over both non-compressed and fixed-size compression baselines.
Dwipam Katariya, T. Caputo, Akshat Shreemali et al.· Proceedings of the 20th ACM...· 0 citations
Sequential RecSys are central to modern personalization, exploiting user's historical interaction sequences to drive next-step decisions. Deep learning models, particularly CNN and Transformer-based architectures, have proven highly effective at capturing temporal dependencies in these histories. For transparency and t...
Akash Pandey, Kanisha Shah, Addrish Roy et al.· 0 citations
Relational Deep Learning (RDL) models multi-table databases as heterogeneous temporal graphs, and graph transformers currently achieve state-of-the-art performance on benchmarks like RelBench. However, the current leading model, RelGT, suffers from two key limitations: its random local sampler yields loosely connected...
It is found that workspace topology measurably affects IPI success, and changes in codebase modularity can significantly alter the Attack Success Rate (ASR), with highly modular environments demonstrating significantly lower attack success rates.
A. R. Day, Pradeep Yadlapalli, Sriram Venkatapathy et al.· 0 citations
This work proposes Sequential Epistemic and Action-Level Validation (SEAV), a verification-centric jailbreak evaluation framework that decomposes responses into ordered steps and evaluates both validity and correctness, and shows that enforcing correctness substantially reshapes measured robustness.
Qilong Wu, Sahil Wadhwa, Pranab Mohanty et al.· 0 citations
REPREC is a lightweight framework that conditions a frozen LLM using compact user-level representations and consistently improves recommendation performance across different sequential encoders, LLM backbones, and user activity levels.
