This work introduces a VLA tool-family interface that exposes explicit tool selection and in-execution progress feedback, enabling efficient event-triggered agent replanning without continuous agent polling and proposes Tool-Aligned Post-Training (TAPT), which constructs invocation-aligned training units for instructio...
Evaluating whether large vision-language models (VLMs) align with human perception for high-level semantic scene comprehension remains a challenge. Traditional white-box interpretability methods are inapplicable to closed-source architectures and passive metrics fail to isolate causal features. We introduce Counterfact...
Ziqi Wen, Parsa Madinei, Miguel P. Eckstein· 0 citations
Discrete MeanFlow is introduced, a theoretical finite-state formulation that replaces point motion with probability-mass transport and validate the identity on exact finite-state Markov chains, demonstrating that the learned kernel recovers the analytical ground truth with high precision.
Fairoz Nower Khan, Nabuat Zaman Nahim, Md Sajid Ahmed et al.· arXiv.org· 2 citations
In settings where labeled verifiable training data is the binding constraint, each checked example should be allocated to the model and reward density where it is most informative. We identify a reward-density principle: sparse sequence-level reward is most useful on models that can explore and discover better behavior...
Yuanda Xu, Hejian Sang, Zhengze Zhou et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Many reinforcement learning (RL) tasks have discrete action spaces, but most generative policy methods based on diffusion and flow matching are designed for continuous control. Meanwhile, generative policies usually rely heavily on offline datasets and offline-to online RL is itself challenging, as the policy must impr...
Fairoz Nower Khan, Nabuat Zaman Nahim, Peizhong Ju· 0 citations
Long video understanding with multimodal language models suffers from three compounding bottlenecks: heavy decode cost to obtain dense RGB frames, token growth with frame count, and weak motion perception under sparse keyframe sampling. Existing remedies either prune visual tokens after decoding, which leaves the expen...
Haopeng Jin, Wenlong Zhao, Tao Yu et al.· 0 citations
We propose a multimodal latent diffusion model that jointly synthesizes volumetric magnetic resonance imaging (MRI) and tabular clinical data within a shared latent space via cross-attention. This approach enables coherent joint representation learning of MRI and tabular modalities for generative modeling. Our model ut...
Daniel Mensing, Jan Kapar, Jochen G. Hirsch et al.· 0 citations
The discount factor in reinforcement learning controls both the effective planning horizon and the strength of bootstrapping, yet most deep RL methods use a single fixed value across all states. State-dependent discounting is a natural way to adapt temporal credit assignment to local state structure, but naively learni...
Yaomin Wang, Jianting Pan, Ran Tian et al.· 0 citations
This work proposes Selective Successor Eligibility Traces (S-trace), an critic-free eligibility trace method that enables more effective credit assignment and establishes an upper bound on its discrepancy from the raw eligibility traces-based policy gradient estimator.
Chao-Li Mou, Xin-Ning Chen, Zhan Zhuang et al.· 5 citations
Current LLM safety benchmarks are predominantly English-centric and often rely on translation, failing to capture country-specific harms. Moreover, they rarely evaluate a model's ability to detect culturally embedded sensitivities as distinct from universal harms. We introduce XL-SafetyBench, a suite of 5,500 test case...
Dasol Choi, Eugenia Kim, Jaewon Noh et al.· 0 citations
Audio description (AD) narrates visual elements in video for blind and low-vision audiences. Recent work has shown that giving novice describers an AI-generated draft to start from helps produce higher-quality AD and lowers the barrier to entry. What remains an open question is how draft quality shapes the editing proc...
Lana Do, Shasta Ihorn, Charity M. Pitcher-Cooper et al.· 0 citations
