Related papers: Self-Refining Vision Language Model for Robotic Fa…

Unmanned Aerial Vehicles (UAVs) depend on onboard sensors for perception, navigation, and control. However, these sensors are susceptible to physical attacks, such as GPS spoofing, that can corrupt state estimates and lead to unsafe…

Reference Audio-Visual Segmentation (Ref-AVS) tasks challenge models to precisely locate sounding objects by integrating visual, auditory, and textual cues. Existing methods often lack genuine semantic understanding, tending to memorize…

We present LARL-RM (Large language model-generated Automaton for Reinforcement Learning with Reward Machine) algorithm in order to encode high-level knowledge into reinforcement learning using automaton to expedite the reinforcement…

Recent advances in synergizing large reasoning models (LRMs) with retrieval-augmented generation (RAG) have shown promising results, yet two critical challenges remain: (1) reasoning models typically operate from a single, unchallenged…

We introduce ASTRO, the "Autoregressive Search-Taught Reasoner", a framework for training language models to reason like search algorithms, explicitly leveraging self-reflection, backtracking, and exploration in their outputs. Recently,…

Accurate and interpretable detection of AI-generated images is essential for mitigating risks associated with AI misuse. However, the substantial domain gap among generative models makes it challenging to develop a generalizable forgery…

While Large language models (LLMs) have the capability to iteratively reflect on their own outputs, recent studies have observed their struggles with knowledge-rich problems without access to external resources. In addition to the…

Large Reasoning Models (LRMs) have recently achieved remarkable success in complex reasoning tasks. However, closer scrutiny reveals persistent failure modes compromising performance and cost: I) Intra-step level, marked by calculation or…

Retrieval-augmented generation (RAG) has become a widely adopted paradigm for enabling knowledge-grounded large language models (LLMs). However, standard RAG pipelines often fail to ensure that model reasoning remains consistent with the…

Large Multimodal Models (LMMs) have recently demonstrated remarkable visual understanding performance on both vision-language and vision-centric tasks. However, they often fall short in integrating advanced, task-specific capabilities for…

Improving embodied reasoning in multimodal-large-language models (MLLMs) is essential for building vision-language-action models (VLAs) on top of them to readily translate multimodal understanding into low-level actions. Accordingly, recent…

Reinforcement learning (RL) has become a key technique for enhancing the reasoning abilities of large language models (LLMs), with policy-gradient algorithms dominating the post-training stage because of their efficiency and effectiveness.…

Autoregressive (AR) language models enforce a fixed left-to-right generation order, creating a fundamental limitation when the required output structure conflicts with natural reasoning (e.g., producing answers before explanations due to…

An impediment to using Large Language Models (LLMs) for reasoning output verification is that LLMs struggle to reliably identify errors in thinking traces, particularly in long outputs, domains requiring expert knowledge, and problems…

Human-robot collaboration in industrial settings requires precise and reliable communication to enhance operational efficiency. While Large Language Models (LLMs) understand general language, they often lack the domain-specific rigidity…

Large Reasoning Models (LRMs) have shown remarkable capabilities in solving complex problems through reinforcement learning (RL), particularly by generating long reasoning traces. However, these extended outputs often exhibit substantial…

Reasoning lies at the heart of intelligence, shaping the ability to make decisions, draw conclusions, and generalize across domains. In artificial intelligence, as systems increasingly operate in open, uncertain, and multimodal…

Large Vision-Language Models (LVLMs) have recently shown great promise in advancing robotics by combining embodied reasoning with robot control. A common approach involves training on embodied reasoning tasks related to robot control using…

Mathematical reasoning is a primary indicator of large language models (LLMs) intelligence. However, existing LLMs exhibit failures of robustness and generalization. This paper attributes these deficiencies to spurious reasoning, i.e.,…

We introduce Robust Multi-Objective Decoding (RMOD), a novel inference-time algorithm that robustly aligns Large Language Models (LLMs) to multiple human objectives (e.g., instruction-following, helpfulness, safety) by maximizing the…