Korea Advanced Institute of Science and Technology

Composed image retrieval takes a reference image plus a modification text and must return the target image, and the common recipe compresses that multimodal query straight into one retrieval vector, leaving the model no explicit chance to work out what the text changes. FactEmbed inserts a set of learnable factorized latents into Qwen2.5-VL-7B's input and trains them with a target-imagination objective that reconstructs target details, so each latent grounds a semantic region, then carries that decomposition into retrieval through a factor-level contrastive loss and attention distillation. On the refined CIRR and FashionIQ benchmarks it scores above both CSMCIR and ReCALL on Recall@1 and average Recall@10, though the improvement margins stated in the text do not match the table values.

Composed image retrieval takes a reference image plus a modification text and must return the target image, and the common recipe compresses that multimodal query straight into one retrieval vector, leaving the model no explicit chance to work out what the text changes. FactEmbed inserts a set of learnable factorized latents into Qwen2.5-VL-7B's input and trains them with a target-imagination objective that reconstructs target details, so each latent grounds a semantic region, then carries that decomposition into retrieval through a factor-level contrastive loss and attention distillation. On the refined CIRR and FashionIQ benchmarks it scores above both CSMCIR and ReCALL on Recall@1 and average Recall@10, though the improvement margins stated in the text do not match the table values.

How well a language-model agent searches depends on the interface it is given, yet existing interfaces are set by hand and applied unchanged to every corpus. SearchWeaver jointly revises corpus artifacts, executable tools and usage instructions using the agent's execution trajectories and task rewards, then selects by downstream search performance. With GPT-5.4-nano, the optimized interfaces raise BrowseComp-Plus answer accuracy from 71.6% to 78.4% and average nDCG@10 across four BRIGHT subsets from 45.7 to 55.0, while cutting tool execution time.

How well a language-model agent searches depends on the interface it is given, yet existing interfaces are set by hand and applied unchanged to every corpus. SearchWeaver jointly revises corpus artifacts, executable tools and usage instructions using the agent's execution trajectories and task rewards, then selects by downstream search performance. With GPT-5.4-nano, the optimized interfaces raise BrowseComp-Plus answer accuracy from 71.6% to 78.4% and average nDCG@10 across four BRIGHT subsets from 45.7 to 55.0, while cutting tool execution time.

Vision-language-action (VLA) policies emit a whole action sequence per query, but how much of it to execute was previously judged only indirectly, through generation stability or prediction agreement. PAV instead predicts, inside the policy's own task-conditioned representation, what a candidate prefix will lead to, and a verifier trained on trajectory-level outcomes scores whether the task can still be completed. On the four LIBERO suites, PAV averages 94.65% success at 14.0 policy queries per episode, above direct verification without future prediction (84.55%, 22.3 queries) and prediction in DINOv2 features (87.00%, 22.2 queries).

Vision-language-action (VLA) policies emit a whole action sequence per query, but how much of it to execute was previously judged only indirectly, through generation stability or prediction agreement. PAV instead predicts, inside the policy's own task-conditioned representation, what a candidate prefix will lead to, and a verifier trained on trajectory-level outcomes scores whether the task can still be completed. On the four LIBERO suites, PAV averages 94.65% success at 14.0 policy queries per episode, above direct verification without future prediction (84.55%, 22.3 queries) and prediction in DINOv2 features (87.00%, 22.2 queries).

Conditional memory lets a language model add capacity through lookup, but the whole embedding table must stay resident; DeepSeek's table alone is 203 GB. Conditional Program stores each row as a short code plus a local scale and reconstructs it with a Gaussian trellis shared across the table, decoding only the rows an input requests. At two bits, storage falls roughly four- to eightfold, most reported task scores stay close to their originals, and output KL is 41–63% lower than 2-bit round-to-nearest.

Conditional memory lets a language model add capacity through lookup, but the whole embedding table must stay resident; DeepSeek's table alone is 203 GB. Conditional Program stores each row as a short code plus a local scale and reconstructs it with a Gaussian trellis shared across the table, decoding only the rows an input requests. At two bits, storage falls roughly four- to eightfold, most reported task scores stay close to their originals, and output KL is 41–63% lower than 2-bit round-to-nearest.

UW-Flow replaces W-Flow's balanced Sinkhorn energy with a debiased unbalanced Sinkhorn divergence, reducing finite-batch velocity error and improving generation on MNIST, CIFAR-10, and ImageNet-100 under matched training budgets.

UW-Flow replaces W-Flow's balanced Sinkhorn energy with a debiased unbalanced Sinkhorn divergence, reducing finite-batch velocity error and improving generation on MNIST, CIFAR-10, and ImageNet-100 under matched training budgets.