- Rating
- 2
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes Query-Aware Streaming Latent Reasoning (QASLR), a post-training framework for long-video embeddings. Selected frames are divided into clips in temporal order and encoded by a frozen vision-language backbone. The resulting features are compressed into evidence tokens that update a fixed-size persistent memory of learnable think tokens, from which an embedding is read out after each clip. Training combines final contrastive learning, step-wise contrastive supervision, and self-distillation from the final embedding. The framework supports both query-independent indexing and query-conditioned candidate scoring. Experiments on nine tasks using Qwen3-VL-Embedding 2B and 8B, as well as RzenEmbed 7B, report improved retrieval performance, while gains over sub-batched single-round post-training are less consistent for video QA.
Critical strengths
- The paper addresses a useful problem: combining evidence from multiple video clips into a fixed-size embedding. The persistent think-token memory provides a clear way to retain information across clips without placing all selected frames in a single backbone context.
- The experiments provide evidence that cross-clip aggregation is useful for retrieval. QASLR improves retrieval performance on both the 2B and 8B backbones, and the appendix compares alternative aggregators and tests memory-reset controls. These results support the value of the proposed memory mechanism.
Critical weaknesses
- The novelty of QASLR is not sufficiently clear. The paper should better explain what is new in its memory design and training objectives.
- The evaluation lacks comparisons with strong existing methods. The architecture and training settings of single-round PT also need more detail. In addition, the role of sub-batching should be clarified so that the gains from streaming latent reasoning can be distinguished from those of the training strategy.
- The experiments do not fully address the challenges of sparse sampling and costly frame encoding. Most results use at most 128 selected frames, so it remains unclear whether QASLR can effectively use more frames at a reasonable cost. Experiments with larger frame budgets and ablations of the think-token count and clip size would help clarify this trade-off.
Questions for authors
- Comparisons with strong existing methods are missing. Could you compare QASLR with relevant long-video retrieval or aggregation methods under the same evaluation protocol?
- Is sub-batching a core contribution or a training strategy supporting streaming latent reasoning? If it is the latter, the main paper should place more emphasis on ablations of the streaming mechanism itself.
- Could you provide more details on single-round PT, including its architecture, trainable modules, frame budget, batch size, negative pool, and training schedule?
- The paper motivates QASLR by missed events under sparse sampling and the cost of encoding more frames. However, it mainly improves aggregation across selected clips, while using at most 128 frames and adding a streaming head. Could you clarify how this design addresses these limitations? Experiments with larger frame budgets and ablations of the think-token count and clip size would help assess the trade-off between performance, memory, and computation.