OccamToken introduces a training-free, adaptive token pruning framework that replaces fixed token budgets with relative evidence testing against a register-based reference, significantly improving VLM…

肖代替了视觉令牌的永久删除，通过可恢复的路由来改进视觉语言模型的性能

The paper introduces Sparse Memory-Efficient Training (SMET), a method that stabilizes and optimizes Dynamic Sparse Training (DST) for large language models, enabling stable and memory-efficient spars…

The paper analyzes token reduction for efficient unified VLM training, finding that while task-specific acceleration saves computation, it destroys the mutual performance gains achieved through joint…

The paper proposes EKSFT, a selective fine-tuning method that masks high-entropy or high-KL divergence tokens during Supervised Fine-Tuning (SFT) to prevent distribution shift and improve subsequent R…

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 introduces NaRA, a noise-aware LoRA technique that dynamically adapts fine-tuning parameters based on the noise level during diffusion, significantly improving the performance of Diffusion L…

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…

DRIFT proposes a novel framework that efficiently optimizes LLMs for multi-turn interactions by decoupling rollout from optimization, allowing the use of weighted supervised fine-tuning to match the p…

The paper introduces ARCA, a novel credit assignment method that measures token salience directly from the adapter's residual hidden state, addressing the degeneracy of standard intrinsic signals when…

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 FoLoRA, a novel optimization framework that uses a generalized Rayleigh quotient to achieve a superior balance between adapting foundation models to specific tasks and preserving…

This paper proposes a new framework called STRIDE for training data attribution in Large Language Models.

PHANTOM is a novel framework that generates highly convincing, context-aware honeytokens by incorporating deep organizational knowledge, significantly improving their believability and detection resis…

This paper introduces Anchored Weight Decay (AWD), a regularization technique that effectively prevents prior-task forgetting during LLM fine-tuning with Evolution Strategies (ES), positioning ES as a…

The paper establishes the first theoretical framework for analyzing the learnability of Test-Time Adaptation (TTA) under non-stationary data streams by introducing Recovery Complexity, which quantifie…

The paper proposes a unified framework for designing efficient and expressive token mixing layers by separating the direct and recurrent influences of inputs, allowing for a principled trade-off betwe…

The paper introduces BiAxisAudit, a novel framework that evaluates LLM bias by analyzing bias scores across multiple prompt formats and within the internal inconsistency of model responses, revealing…

The paper introduces Chunk-Level Guided Generation, a training-free method that uses an off-the-shelf large language model (LLM) as a process scorer to guide small model generation, achieving performa…