Related papers: Semantics-Adaptive Activation Intervention for LLM…

Effectively integrating Large Language Models (LLMs) into autonomous driving requires a balance between leveraging high-level reasoning and maintaining real-time efficiency. Existing approaches either activate LLMs too frequently, causing…

Steering, or direct manipulation of internal activations to guide LLM responses toward specific semantic concepts, is emerging as a promising avenue for both understanding how semantic concepts are stored within LLMs and advancing LLM…

Mechanistic Interpretability (MI) has emerged as a vital approach to demystify the opaque decision-making of Large Language Models (LLMs). However, existing reviews primarily treat MI as an observational science, summarizing analytical…

Large language models (LLMs) have shown potential in supporting decision-making applications, particularly as personal assistants in the financial, healthcare, and legal domains. While prompt engineering strategies have enhanced the…

Activation steering methods are widely used to control large language model (LLM) behavior and are often interpreted as revealing meaningful internal representations. This interpretation assumes that steering directions are identifiable and…

Activation steering methods enable inference-time control of large language model (LLM) behavior without retraining, but current approaches face a fundamental trade-off: sample-efficient methods suboptimally capture steering signals from…

Steering vectors (SVs) offer a lightweight way to control large language models (LLMs) at inference time by shifting hidden activations, providing a practical middle ground between prompting and fine-tuning. Yet SVs can be unreliable in…

Large Language Model (LLM) agents are commonly tuned with supervised finetuning on ReAct-style expert trajectories or preference optimization over pairwise rollouts. Most of these methods focus on imitating specific expert behaviors or…

Recent work in activation steering has demonstrated the potential to better control the outputs of Large Language Models (LLMs), but it involves finding steering vectors. This is difficult because engineers do not typically know how…

Transformers have achieved state-of-the-art performance across language and vision tasks. This success drives the imperative to interpret their internal mechanisms with the dual goals of enhancing performance and improving behavioral…

Large language models (LLMs) exhibit reasoning biases, often conflating content plausibility with formal logical validity. This can lead to wrong inferences in critical domains, where plausible arguments are incorrectly deemed logically…

Large Language Models (LLMs) have demonstrated powerful reasoning capabilities through Chain-of-Thought (CoT) in various tasks, yet the inefficiency of token-by-token generation hinders real-world deployment in latency-sensitive recommender…

Large Language Models (LLMs) achieve remarkable performance through pretraining on extensive data. This enables efficient adaptation to diverse downstream tasks. However, the lack of interpretability in their underlying mechanisms limits…

Semantic segmentation plays an important role in intelligent vehicles, providing pixel-level semantic information about the environment. However, the labeling budget is expensive and time-consuming when semantic segmentation model is…

Large Language Models (LLMs) have exhibited impressive capabilities across diverse application domains. Recent work has explored Multi-LLM Agent Debate (MAD) as a way to enhance performance by enabling multiple LLMs to discuss and refine…

Fine-tuning large language models (LLMs) to adapt to evolving safety policies is costly and impractical. Mechanistic interpretability enables inference-time control through latent activation steering, yet its potential for precise,…

Changing the behavior of large language models (LLMs) can be as straightforward as editing the Transformer's residual streams using appropriately constructed "steering vectors." These modifications to internal neural activations, a form of…

For speech interaction, voice activity detection (VAD) is often used as a front-end. However, traditional VAD algorithms usually need to wait for a continuous tail silence to reach a preset maximum duration before segmentation, resulting in…

Multimodal Large Language Models (MLLMs) demonstrate impressive cross-modal capabilities, yet their substantial size poses significant deployment challenges. Knowledge distillation (KD) is a promising solution for compressing these models,…

Understanding human actions is critical for advancing behavior analysis in human-robot interaction. Particularly in tasks that demand quick and proactive feedback, robots must recognize human actions as early as possible from incomplete…