The paper proposes a novel zeroth-order optimization framework to enhance the robustness of LLM safety alignment, showing that few refinement steps can significantly improve safety while maintaining u…

The paper introduces SkillBrew, a multi-objective framework that treats skill bank curation as a constrained optimization problem to build efficient and well-curated skill repositories for LLM agents.

The paper introduces RA-MoE, a novel fine-tuning framework that leverages the internal routing structure of Mixture-of-Experts (MoE) models to improve performance on multilingual downstream tasks by a…

MOSAIC is a novel scheduling framework that significantly accelerates Mixture-of-Agents (MoA) workloads by jointly optimizing expert placement and utilizing confidence-aware adaptive aggregation.

The paper investigates how various fine-tuning methods can be used both to intentionally misalign and subsequently realign large language models (LLMs), revealing distinct strengths for attack and def…

The paper introduces NeWTral, a framework that restores safety alignment to specialized LLM adapters without sacrificing their domain-specific knowledge, achieving a significant reduction in attack su…

The paper introduces the Configurable Safety Reward Model (CSRM), a novel reward model that can be jointly optimized for calibrated safety compliance and reward modeling, significantly improving LLM s…

AI-PROPELLER introduces a novel interprocedural code layout optimization system that uses an agentic evolutionary workflow to achieve significant, measurable performance gains in large-scale, real-wor…

The paper introduces RAG-Pref, a novel, training-free Retrieval Augmented Generation (RAG) method for preference alignment that significantly improves LLM refusal guardrails against agentic attacks wi…

The paper introduces Safety Bottleneck Regularization (SBR), a novel defense mechanism that anchors LLM safety by constraining the unembedding layer, effectively preventing harmful fine-tuning (HFT) e…

The paper introduces MOSAIC-Bench, a benchmark demonstrating that coding agents can ship exploitable code by complying with seemingly innocuous, staged tasks, a vulnerability that is not easily mitiga…

The paper reframes LLM reliability from an impossible universal problem to a manageable, local patch-based problem, showing that sufficient interventions can be found by focusing on recurring failure…

The paper introduces R$^2$A, an adversarial attack that uses suffix optimization to mislead black-box LLM routers into consistently selecting expensive, high-capability models.

CRAM proposes a novel framework for Multimodal Continual Instruction Tuning that balances task isolation and parameter efficiency by using centroid-guided routing and adaptive MoE to prevent catastrop…

The paper proposes formulating RAG design as an architecture search problem and introduces RAISE, a comprehensive framework and benchmark for systematically optimizing RAG hyperparameters.

MESA is a targeted alignment framework that decentralizes safety responsibilities across multiple experts in Mixture-of-Experts (MoE) LLMs using Optimal Transport theory, thereby improving safety robu…

SafeSteer proposes a localized on-policy distillation method that restricts safety alignment to specific safety tokens, thereby achieving strong safety performance with minimal degradation to general…

The paper proposes a unified framework to systematically redefine instance matching for Panoptic Quality evaluation, moving beyond the standard One-to-One matching to accommodate complex scenarios lik…

SIRIUS-SQL introduces a robust multi-candidate text-to-SQL system that addresses weaknesses in candidate generation, error handling, and selection, achieving state-of-the-art performance on complex be…

The paper formally models structure-informed multiple sequence alignment (MSA-S) as an NP-complete optimization problem, establishing a strong computational complexity baseline for the field.