Related papers: Think-Reflect-Revise: A Policy-Guided Reflective F…

Large vision-language models (LVLMs) are increasingly deployed in globally distributed applications, such as tourism assistants, yet their ability to produce culturally appropriate responses remains underexplored. Existing multimodal safety…

Reinforcement learning from human feedback (RLHF) has become a powerful post-training paradigm for aligning large language models with human preferences. A core challenge in RLHF is constructing accurate reward signals, where the…

Large Reasoning Models (LRMs) have recently shown impressive performance on complex reasoning tasks, often by engaging in self-reflective behaviors such as self-critique and backtracking. However, not all reflections are beneficial-many are…

This paper provides a systematic survey of jailbreak attacks and defenses on Large Language Models (LLMs) and Vision-Language Models (VLMs), emphasizing that jailbreak vulnerabilities stem from structural factors such as incomplete training…

We introduce OpenVLThinker, one of the first open-source large vision-language models (LVLMs) to exhibit sophisticated chain-of-thought reasoning, achieving notable performance gains on challenging visual reasoning tasks. While text-based…

Large language models (LLMs) increasingly solve complex reasoning tasks via long chain-of-thought, but their forward-only autoregressive generation process is fragile; early token errors can cascade, which creates a clear need for…

Recent advances in large Vision-Language Models (VLMs) have exhibited strong reasoning capabilities on complex visual tasks by thinking with images in their Chain-of-Thought (CoT), which is achieved by actively invoking tools to analyze…

Large Language Models have shown impressive generative capabilities across diverse tasks, but their safety remains a critical concern. Existing post-training alignment methods, such as SFT and RLHF, reduce harmful outputs yet leave LLMs…

Large Reasoning Models (LRMs) have demonstrated remarkable capabilities in solving complex problems by generating structured, step-by-step reasoning content. However, exposing a model's internal reasoning process introduces additional…

We present InvThink, a training and prompting framework that requires the model to enumerate, analyze, and constrain potential failures before generating its final response. Unlike existing safety alignment methods that optimize only for…

While Large Language Models (LLMs) demonstrate exceptional performance in surface-level text generation, their nature in handling complex multi-step reasoning tasks often remains one of ``statistical fitting'' rather than systematic logical…

Large language models (LLMs) achieve strong performance by generating long chains of thought, but longer traces always introduce redundant or ineffective reasoning steps. One typical behavior is that they often perform unnecessary…

Ensuring the safety of large language models (LLMs) is critical as they are deployed in real-world applications. Existing guardrails rely on rule-based filtering or single-pass classification, limiting their ability to handle nuanced safety…

Large Reasoning Models like DeepSeek-R1 mark a fundamental shift in how LLMs approach complex problems. Instead of directly producing an answer for a given input, DeepSeek-R1 creates detailed multi-step reasoning chains, seemingly…

Reinforcement Learning (RL) has shown promise in improving the reasoning abilities of Large Language Models (LLMs). However, the specific challenges of adapting RL to multimodal data and formats remain relatively unexplored. In this work,…

Large Language Models (LLMs) face a significant threat from multi-turn jailbreak attacks, where adversaries progressively steer conversations to elicit harmful outputs. However, the practical effectiveness of existing attacks is undermined…

Large Language Models (LLMs) show great promise in complex reasoning, with Reinforcement Learning with Verifiable Rewards (RLVR) being a key enhancement strategy. However, a prevalent issue is ``superficial self-reflection'', where models…

Large Reasoning Models (LRMs) are designed to solve complex tasks by generating explicit reasoning traces before producing final answers. However, we reveal a critical vulnerability in LRMs -- termed Unthinking Vulnerability -- wherein the…

When making significant life decisions, people increasingly turn to conversational AI tools, such as large language models (LLMs). However, LLMs often steer users toward solutions, limiting metacognitive awareness of their own…

Current safety alignment techniques for large language models (LLMs) face two key challenges: (1) under-generalization, which leaves models vulnerable to novel jailbreak attacks, and (2) over-alignment, which leads to the excessive refusal…