Vision-language models, speech and cross-modal systems that read, look and listen in the same forward pass.
arXiv:2609.16070v1 Announce Type: cross Abstract: Generative recommendation reformulates item prediction as semantic identifier generation, yet episodic content introduces a fundamentally different s...
arXiv:2609.16841v1 Announce Type: cross Abstract: Increasing image resolution produces ever-longer visual-token sequences in vision-language models (VLMs), substantially raising their inference cost....
arXiv:2602.06652v2 Announce Type: replace Abstract: The robustness of Vision Language Models (VLMs) is commonly assessed through output-level invariance, implicitly assuming that stable predictions r...
arXiv:2609.16689v1 Announce Type: new Abstract: Large-scale vision-language models (VLM) such as CLIP enable strong open-vocabulary reasoning, yet deploying these capabilities on resource-constrained...
arXiv:2609.17269v1 Announce Type: new Abstract: Multimodal large language models generate natural-language responses from visual inputs, yet may mention objects absent from an image. In medication as...
arXiv:2609.17443v1 Announce Type: new Abstract: Vision-language models (VLMs) achieve strong visual question answering (VQA) performance, but processing large cluttered images is computationally expe...
The paper introduces ViD, a vision‑dominant gender bias mitigation framework for large vision‑language models. ViD uses causal analysis of attention patterns and dual mechanisms—backdoor adjustment and refined token selection—to suppress bias while preserving reasoning and generation quality. Experiments show a 14.7% reduction in gender bias on FACET and significant improvements on MS COCO image captioning, all without extra training overhead.
The paper introduces Affect-Prototype Guided Fusion (APCF), a framework for open‑vocabulary multimodal emotion recognition that handles incomplete and unsynchronized modal data. APCF builds an affect‑prototype library to model how different emotions contribute across modalities, enabling dynamic fusion of available features. The fused representations are then decoded by an LLM to generate open‑vocabulary emotion labels, achieving superior performance on OV‑MERD+ and MER‑FG datasets compared to existing methods.
EviDep is a multimodal evidential regression framework for estimating depression severity from audio–visual recordings, incorporating multi‑scale temporal modeling and shared–private representation learning. It uses frequency‑aware feature extraction to decompose behavioral sequences into multiple frequency bands, refined by scale‑specific experts, and applies disentangled evidential learning to separate cross‑modal shared and modality‑specific information. The model outputs Normal‑Inverse‑Gamma distributions via multi‑branch evidential regression, enabling estimation of depression severity along with aleatoric and epistemic uncertainty, and demonstrates competitive accuracy on several benchmark datasets.
arXiv:2601.09050v2 Announce Type: replace Abstract: Tonal low-resource languages are widely spoken but remain underserved by modern speech technologies. A central challenge is learning speech represe...
The paper introduces little m, an AI agent that helps formulate industrial process control models by combining a domain-specific knowledge repository with LLM-driven interaction. It tackles the challenge of converting messy real-world specifications, including natural language and spatial diagrams, into rigorous mathematical optimization models. The authors also present IPC-Bench, a multimodal dataset of 50 canonical scenarios, and show through automated and human evaluations that little m outperforms state‑of‑the‑art LLMs in generating semantically correct models.
The paper reports a submission to the SHROOM-Visions shared task, aiming to detect and classify hallucinated character spans in vision‑language model outputs across four languages. The authors use multiple fine‑tuned vision‑language models as independent annotators, combine their predictions via character‑level majority voting, and also investigate activation probes. Their method achieved first place in three of the four languages and consistently ranked on the podium for all languages and metrics, with analysis showing that model disagreement mirrors human annotator disagreement.
The paper examines how the tight integration of multimodal understanding and image generation in Unified Multimodal Models (UMMs) can create new safety vulnerabilities. It introduces RICE, an attack framework that exploits bidirectional interactions between generation and understanding to propagate unsafe signals across modalities. Experiments demonstrate high attack success rates in both Generation‑to‑Understanding and Understanding‑to‑Generation pathways, revealing previously overlooked safety weaknesses in UMMs.
The paper introduces a new paradigm called VLM-as-probabilistic-grounder, which models the uncertainty of Vision‑Language Model (VLM) predicate groundings as a probability distribution over symbolic states. This probabilistic grounding allows belief‑space planning, producing more robust plans in partially observable settings. Experiments in simulated household robot environments demonstrate that this approach improves robustness and task success compared to deterministic grounding methods.
EgoPathBench is a new dataset and benchmark that tests zero‑shot egocentric waypoint decision‑making in vision‑language models. Each task presents an egocentric RGB image, a natural‑language goal, and numbered visible waypoints, and models must return traversable candidates or an ordered route. The benchmark evaluates candidate feasibility, edge legality, and goal arrival under point‑agent or embodied geometry, covering 31,852 training, 1,345 validation, and 1,111 benchmark questions. "whyItMatters":"The benchmark reveals that current VLMs perform poorly on integrated navigation tasks, highlighting a gap in spatial intelligence that can be addressed by fine‑tuning with the released training data."
The paper introduces ResLRP, an extension of Layer-wise Relevance Propagation that explicitly handles residual connections in Vision Transformers to prevent attribution explosion. It demonstrates that residual cancellation causes instability in ViT explanations, and that ResLRP improves faithfulness and localization across a wide range of ViT architectures, including Vision Language Models. The method also provides a diagnostic measure for predicting attribution degradation and successfully localizes Sparse Autoencoder features.
FluxVLA Engine is an open, configuration‑driven platform that unifies the fragmented components of embodied policy development—datasets, visual‑language and world models, action heads, learning methods, distributed training, simulation evaluation, inference, and robot interfaces—into a reproducible data‑to‑deployment workflow. It adds features such as compositional dual‑arm simulation, scalable automatic data generation, human‑in‑the‑loop rollout and correction, Real‑Time Chunking for fast inference, and lightweight remote GPU serving, thereby linking offline learning, simulation validation, online correction, and real‑robot execution under shared, auditable contracts. The engine aims to eliminate engineering bottlenecks that currently separate promising embodied‑learning algorithms from reliable, reproducible deployment.
RiskChainBench is a new benchmark that pairs 3,600 synthetic token‑text restoration inputs with 600 human‑labeled local web environments to evaluate how well models can recover obfuscated platform messages and then investigate the associated websites. The benchmark measures both message restoration accuracy and the subsequent web‑investigation decision, using a fixed multimodal evidence judge to assess faithfulness, sufficiency, completeness, and consistency. Across ten models, performance varies widely, with entry recovery ranging from 35.2% to 95.2% and web decision accuracy from 26.3% to 62.8%, highlighting execution failures as the main bottleneck.
arXiv:2609.16055v1 Announce Type: cross Abstract: Test-time compute has emerged as a major approach to improving the capabilities of Large Language Models (LLMs). However, existing test-time reasonin...
BiCLIP is a bidirectional multimodal framework that enhances medical image segmentation by allowing visual features to iteratively refine textual representations, improving semantic alignment. It incorporates an augmentation consistency objective to stabilize learning against perturbed inputs. Experiments on QaTa-COV19 and MosMedData+ show that BiCLIP outperforms state‑of‑the‑art image‑only and multimodal baselines, achieving strong performance even with only 1% labeled data and resisting common clinical artifacts such as motion blur and low‑dose CT noise.