The paper introduces SCALAR, a query‑conditioned spherical centroid aggregator that assigns relevance‑based weights to each available modality before computing a spherical centroid. SCALAR supports arbitrary modality subsets, is trained with rank‑8 LoRA adapters on masked views, and achieves positive aggregation gains on four of five benchmarks, outperforming prior symmetric aggregators. With only 4.8 million trainable parameters, SCALAR attains the highest text‑to‑video R@1 on three benchmarks and surpasses the released GRAM checkpoint under test‑time modality dropout by 3.2 to 10.9 R@1.
arXiv:2609.15320v1 Announce Type: new Abstract: Volume-based multimodal retrieval jointly scores a text query with a candidate's video, audio, and subtitle embeddings. While this approach captures hi...
arXiv:2608.23484v1 Announce Type: new Abstract: We present Team Semiintelligencn's solution for the ACM RecSys 2026 TalkPlayData Challenge, addressing conversational music recommendation through a mu...
We present Team Semiintelligencn's solution for the ACM RecSys 2026 TalkPlayData Challenge, addressing conversational music recommendation through a multi-modal and personalized conversational recomme...
arXiv:2607. 25266v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) have enabled long-form video understanding at a scale that was not previously possible.
arXiv:2608. 12987v1 Announce Type: cross Abstract: Generative information retrieval (GIR) has emerged as a compelling alternative to the conventional index-retrieve-then-rank retrieval pipeline by training a generator to produce the identifiers of relevant items directly.
arXiv:2609.10224v1 Announce Type: new Abstract: Vision-language models such as CLIP embed images and text in a shared space, where modality-specific distributions often remain separated. Existing acc...
The paper introduces D3-Omni, a balanced and decoupled benchmark designed to diagnose fine‑grained multimodal understanding in OmniJudges that evaluate text‑to‑image, text‑to‑video, and text‑to‑speech generation. D3-Omni covers 53 orthogonal binary dimensions across 10,671 samples, using fixed positive seeds and controlled prompt rewriting to generate negatives, thereby ensuring each error can be attributed to a single capability. The benchmark’s dual‑balanced, decoupled, and dynamic design achieves near 1:1 per‑dimension parity and a uniform total‑score distribution, revealing that strong OmniJudges often miss modality‑related failures and treat distinct attributes as a single decision, masking systematic blind spots.
arXiv:2609.36815v1 Announce Type: new Abstract: Partially Relevant Video Retrieval (PRVR) seeks to retrieve untrim-med videos containing a moment that matches a text query, without temporal annotatio...
The paper investigates how the modality gap— the separation between image and text representations in contrastive vision‑language models—affects different downstream tasks. By showing that a single dominant direction accounts for most of the image‑text mean separation, the authors explain why reducing or removing this gap can improve zero‑shot classification, degrade retrieval, or restore performance depending on the task. The study provides a geometric framework that clarifies when and why gap interventions should be applied in vision‑language systems.
arXiv:2606. 05931v1 Announce Type: cross Abstract: When retrieving a person from a video archive by voice and face, should the system be multimodal or not?
The paper introduces GradCIR, a method for training composed image retrieval (CIR) systems on graded relevance rather than binary relevance. It uses a vision‑language model to generate queries and 4‑level relevance labels, an iterative feedback loop to mine hard negatives, and a hierarchy‑aware angular objective to directly optimize graded labels. Experiments on a Walmart catalog and FashionIQ show significant NDCG improvements and the system is deployed in Walmart’s live visual‑search traffic.
MARS introduces a multi‑layer, multi‑slot embedding framework for text‑video retrieval that constructs adaptive representation slots by combining hidden states from different decoder layers. By comparing corresponding text and video slots and aggregating their similarities, MARS captures fine‑grained cues that single‑token embeddings miss. A hard‑negative‑aware slot specialization objective further encourages slots to focus on discriminative matching cues, leading to state‑of‑the‑art results on four benchmarks.