Vision-language models, speech and cross-modal systems that read, look and listen in the same forward pass.
arXiv:2608.29537v1 Announce Type: cross Abstract: Frozen vision-language-action (VLA) policies offer broad manipulation skills but execute open-loop action chunks without tracking task progress, so t...
arXiv:2608.29220v1 Announce Type: new Abstract: Multimodal image fusion (MMIF) aims to integrate complementary sensor data into a single representation that preserves intrinsic scene reality while el...
SocialReasonBench is a new video‑multiple‑choice QA benchmark designed to test socially grounded reasoning in interactive narrative videos. It uses branching gameplay footage from *Detroit: Become Human*, where player choices create alternative social outcomes that can be verified against the game’s script and flowchart. The benchmark includes seven reasoning dimensions—such as intent recognition, emotional empathy, moral dilemma, counterfactual reasoning, and causal antecedent—and employs a multi‑agent pipeline to curate clips, ground answer labels, and generate theory‑guided questions with diagnostic distractors.
The paper introduces CERES, a closed‑loop multimodal indexing framework that addresses semantic collapse in multimodal generation by building a three‑level semantic pyramid and using scale‑routed cross‑attention to generate images that remain retrievable by their original queries. CERES employs a co‑occurrence‑aware router, a lightweight U‑Net generator, and a soft‑Jaccard coverage objective to ensure generated images cover the intended concepts, verified by re‑indexing with a frozen vision‑language model and an external DINOv2 probe. Experiments on four pansharpening benchmarks show state‑of‑the‑art performance, especially under extreme scale variation, and significant improvements in concept‑query retrieval and image‑text ranking metrics.
arXiv:2608.28678v1 Announce Type: new Abstract: Scalable Vector Graphics (SVGs) power much of the modern visual ecosystem, yet state-of-the-art generative models focus almost entirely on rasterized i...
The study investigates how multimodal large language models (MLLMs) use prosodic cues in sarcasm detection. By testing Qwen2.5‑Omni and Qwen3‑Omni on Mandarin Chinese and English across five modality conditions, the authors find that adding audio increases false positives without improving true positives. Acoustic error analysis shows that models rely on a stereotypical prosodic pattern—elevated pitch and irregular pausing—that does not align with genuine sarcasm cues, and manipulating these dimensions alone can raise false positive rates up to 60%. The same effect appears in Gemini 3 Flash Preview, indicating the heuristic is not limited to a single architecture.
TEMPO is a unified model that adds temporally‑grounded capabilities to large audio‑language models, enabling timestamping of events, speakers, and sounds in audio, speech, and music. It introduces a supervised fine‑tuning stage featuring atomic timestamp tokens, a time‑aware projector with sinusoidal encodings, and a distance‑aware Gaussian loss, trained via a synthetic‑to‑real curriculum. Additionally, TEMPO employs reinforcement learning (GRPO) as a refinement step, and achieves state‑of‑the‑art performance on a benchmark of 10K samples across five timestamping tasks, surpassing Audio Flamingo Next and Qwen3‑Omni.
SafeAtlas-VL introduces a large multimodal safety dataset with 1.5 million instances, rating image, request, and response risks on a five‑level ordinal scale across 15 harm categories and 55 subcategories. The accompanying SafeAtlas‑Bench provides 5,000 held‑out cases for evaluating ordinal predictions and continuous risk scores. Models trained on this data, including an 8B Guard model, achieve state‑of‑the‑art performance, outperforming prior benchmarks by about 4% in F1 score.
arXiv:2601.03549v3 Announce Type: replace-cross Abstract: Sign Language Translation (SLT) is a challenging cross-modal task requiring joint modeling of manual articulations and non-manual signals. Ex...
arXiv:2608.18734v2 Announce Type: replace Abstract: 4D understanding and reasoning is a fundamental capability for embodied AI agents operating in dynamic physical environments. However, existing vis...
arXiv:2601.15897v3 Announce Type: replace Abstract: Multi-modal scene reconstruction integrating RGB and thermal infrared data is essential for robust environmental perception across diverse lighting...
arXiv:2606.15872v2 Announce Type: replace Abstract: Frontier scientific reasoning remains a major challenge for large language models (LLMs), where even the strongest commercial systems fall short of...
arXiv:2608.29092v1 Announce Type: new Abstract: Large vision-language models (LVLMs) frequently generate content unsupported by visual inputs. Preliminary experiments show that visual evidence is pri...
arXiv:2608.30912v1 Announce Type: new Abstract: Artificial intelligence (AI) and natural language processing (NLP) are increasingly used to extract, integrate, and interpret biomedical knowledge rele...
arXiv:2604.19782v2 Announce Type: replace-cross Abstract: Recent advances in large audio language models (LALMs) have enabled multilingual speech understanding. However, benchmarks for evaluating LAL...
arXiv:2608.29601v1 Announce Type: cross Abstract: We present $\mathcal{N}_0$-Foundation, a paradigm for tactile-enabled embodied manipulation, which integrates tactile sensing hardware, large-scale m...
arXiv:2608.31065v1 Announce Type: new Abstract: Surgical phase recognition is key to context-aware computer-assisted feedback in vitreoretinal procedures, yet the scarcity of synchronized multimodal...
arXiv:2608.30686v1 Announce Type: cross Abstract: Coding agents are increasingly used for software engineering tasks, including bootstrapping projects from third-party repositories whose integrity ca...
arXiv:2608.31035v1 Announce Type: new Abstract: Codec-based text-to-speech (TTS) models make language-model post-training applicable to speech generation, but it remains unclear when learned perceptu...
Context-Aware Interleaved Batching for WhisperX proposes a new batching strategy that combines WhisperX’s fast intra-audio batching with Whisper’s sequential context retention. By using voice activity detection (VAD) to define segment boundaries, the algorithm stabilizes Whisper’s text conditioning and preserves continuous historical context across batched audio segments. Experiments on long‑form audio benchmarks show reduced Word Error Rate and improved proper noun transcription while maintaining high‑throughput inference speeds.