Vision-language models, speech and cross-modal systems that read, look and listen in the same forward pass.
arXiv:2608. 15037v1 Announce Type: cross Abstract: Audio-Text Foundation Models (ATMs) fail catastrophically under severe acoustic noise, yet existing adaptation strategies either rely on gradient-based Test-Time Adaptation (TTA), which reinforces noise rather than signal, or on prompt tuning that requires privileged noise annotations unavailable at inference.
arXiv:2608. 16407v1 Announce Type: cross Abstract: Point-of-interest (POI) recommendation models based on graph neural networks achieve strong performance by propagating collaborative signals over user-item interactions, yet they struggle with the cold-start problem, where items with few or no interactions are not represented.
arXiv:2508. 09521v3 Announce Type: replace-cross Abstract: Emotional support conversations require more than fluent responses.
arXiv:2608. 16201v1 Announce Type: new Abstract: Multimodal sentiment analysis (MSA) aims to predict sentiment polarity and intensity from heterogeneous inputs such as text, audio, and vision.
arXiv:2608. 15310v1 Announce Type: cross Abstract: Multimodal data collected by heterogeneous devices are used for collaborative training, where federated learning (FL) serves as a key paradigm for effective distributed modeling with data privacy preservation.
arXiv:2608. 15056v1 Announce Type: new Abstract: Multimodal retrieval-augmented generation (RAG) systems often rely on long unstructured contexts or aggressively expanded evidence graphs, which can introduce noisy evidence, weaken multi-hop reasoning, and increase unsupported generation.
arXiv:2506. 03096v2 Announce Type: replace-cross Abstract: Contrastive language-image pre-training aligns features of text-image pairs in a common latent space via distinct encoders for each modality.
arXiv:2608. 14586v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models are becoming a promising paradigm for autonomous driving, but their deployment on existing vehicle platforms remains difficult because they introduce both high inference latency and strong GPU-side resource pressure.
arXiv:2502. 11603v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) exhibit strong natural language understanding capabilities but also inherit and amplify societal biases, particularly gender bias, raising fairness concerns.
The paper investigates how encoder-decoder models in ASR and NMT can generate fluent text even when the input contains no recoverable message, a phenomenon known as message-free hallucination. By auditing the models’ reserved null tokens and manipulating their scores, the authors show that a higher null-token score can suppress fabrication but may also delete valid content or shorten translations. The study highlights that the null token can serve as a diagnostic tool for hallucination and suggests evaluating abstention methods by considering both suppression and deletion costs.
arXiv:2608. 14741v1 Announce Type: cross Abstract: We introduce PolyComp, a procedurally generated and verified benchmark that stresses visual recognition and compositional spatial reasoning.
Textual context such as news, reports, and logs can provide valuable signals for time series forecasting, especially when future dynamics are driven by external events that are not yet visible in hist...
Long-horizon robot manipulation chains many contact-rich skills into one multi-stage task. Vision-language-action (VLA) models increasingly master the individual skills, yet the chain still fails: err...
Humanoid robots hold great promise as general-purpose agents in human-centered environments, yet generalist vision-language-action (VLA) foundation models are not readily applicable to humanoid whole-body loco-manipulation. The high dimensionality and interdependence of humanoid motions make it challenging for conventional single-stage VLA architectures to coordinate locomotion, waist posture, and dual-arm manipulation effectively.
Large vision-language models can recognize the objects and attributes in a crowded scene yet assign an attribute to the wrong same-class instance. Generic visual-question-answering accuracy marks the...
Language and vision-language models generate plausible embodied plans but do not guarantee executability, as their outputs can violate environment dynamics or act on incorrectly grounded entities. We present a neurosymbolic agent that factors long-horizon household tasks into task-directed visual exploration and constrained symbolic planning.
Despite progress in instruction-based video editing, unimodal textual instructions inherently struggle to convey fine-grained textures and complex dynamics. To bridge this perceptual gap, we propose Visual In-context Editing, a new paradigm elevating video editing from textual instructions to multi-modal visual guidance encompassing single image, image pair, and video pair.
Vision-Language-Action models (VLAs) integrate visual perception, language instruction, and action generation into end-to-end policies across heterogeneous architectures. However, enabling VLAs to self-evaluate their action generation reliability without external supervision remains a major challenge.
Empathetic social robots should respond not only to what users say, but also to how their emotions dynamically evolve during interaction. However, existing empathetic dialogue systems are often text-c...
Multimodal Retrieval Augmented Generation (M-RAG) is increasingly vulnerable to adversarial attacks where malicious data are crafted to produce embeddings that align with benign entries in the vector...