Large Language Models

The paper introduces the Attention Redistribution Attack (ARA), a white-box adversarial method that bypasses safety alignments in LLMs by manipulating the attention mechanism's geometry, showing that…

The paper introduces Set-Distance Rewards (SDR), a permutation-invariant reward signal that effectively guides the generation of unordered radiology reports, significantly outperforming standard train…

The paper introduces Humanoid-GPT, a large-scale generative Transformer model that achieves robust zero-shot motion tracking and control by training on a massive, unified corpus of motion data.

ARES is a novel framework that systematically discovers and mitigates dual vulnerabilities in RLHF systems by simultaneously testing the core LLM and its Reward Model (RM) using structured adversarial…

The paper introduces SeedHijack, a backdoor attack that manipulates the pseudorandom number generation process in LLMs to force specific token selections, and proposes a hardware quantum random number…

The paper proposes using GPT-4o to generate controlled paraphrases of target text for sign language translation (SLT) augmentation, achieving significant BLEU-4 improvements on PHOENIX14T.

The paper proposes In-Context Reward Adaptation, a transformer-based framework that uses in-context learning and auxiliary signals (like human response time) to robustly model diverse and unseen human…

The paper benchmarks local, offline LLMs for confidential translation workflows, demonstrating that while they are viable for privacy-sensitive use, they generally lag behind top commercial NMT system…

The paper presents Tahoe, a system that optimizes Text-to-SQL performance through dynamic data management and hint learning.

The paper introduces Head-Masked Nullspace Steering (HMNS), a novel geometry-aware attack method that achieves state-of-the-art jailbreak success rates by manipulating the internal attention mechanism…

HMPO introduces a single-stage, cost-effective reinforcement learning framework that achieves significant token compression of Chain-of-Thought reasoning with minimal loss of accuracy, applicable acro…

The paper introduces the threat model of sequential data poisoning, demonstrating that multiple, collaborating attackers can exploit compound vulnerabilities in LLM post-training pipelines that are in…

The paper proposes an uncertainty-aware transfer learning framework using the Temporal Fusion Transformer (TFT) to achieve robust and scalable energy forecasting across different buildings, demonstrat…

This paper re-examines the role of temperature ($ au$) in LLM distillation, demonstrating that while Reverse KL (RKL) is often preferred, Forward KL (FKL) significantly outperforms RKL at higher tempe…

The paper proposes MADS, a Model-Aware Diverse Core Set Selection method that uses LLM internal activation states to select a small, diverse core set of instructions, significantly improving model per…

The paper proposes the Expected Safety Impact (ESI) framework to identify safety-critical parameters in LLMs, introducing targeted tuning methods (SET and SPA) to enhance safety and preserve alignment…

This paper investigates the privacy risk of reconstructing Personally Identifiable Information (PII) from Large Language Models (LLMs) that have undergone Supervised Finetuning (SFT), proposing a nove…

The paper systematically maps LLM agent vulnerabilities by testing 10,000 prompt variations, finding that 'goal reframing' language is the primary trigger for exploitation, rather than broad adversari…

This paper demonstrates that targeted adaptation of the small language model Phi Silica, using dataset curation and fine-tuning, significantly improves its performance in short-form text rewriting, na…

The paper introduces DistractionIF, a benchmark showing that larger LLMs are paradoxically less robust to benign, instruction-like noise in reference text, suggesting reinforcement learning can restor…