Training & fine-tuning
Adapts a VPG-learning workflow to a fully black-box setting by replacing a white-box equivalence oracle with PAC-style sampling over trees, querying only the acceptor’s binary accept/reject decisions. It further improves robustness by sampling trees directly (rather than well-formed sequences constrained by a permissive baseline automaton), using the resulting queries to estimate deviation from a target VPG model.
AI summary
Inference efficiency
Convert eligibility determination into a multiple-choice scoring problem and use a pointer head to assign scores to candidate natural-language options in a single forward pass. This avoids autoregressive verdict generation by directly producing option logits for a fixed set of answers.
AI summary
Inference efficiency
Create a shared inertial input space for both human and humanoid motion by synthesizing kinematic IMU signals at corresponding body sites, then train a single continuous-time encoder to jointly predict velocity and align motion with text within that shared space.
AI summary
Reasoning & planning
Use two training subsets—one containing a target trait linked to a trigger co-occurring with the trait, and a second “clean” subset that matches formatting but lacks the trigger—to create a situation where the combined training causes the model to learn or activate the trait/backdoor, even if the poisoned subset alone shows little effect.
AI summary
Retrieval & memory
Estimate latent physical interaction parameters from pre-contact vision by replacing fixed semantic classes with a Gaussian-mixture posterior whose components are drawn from past, interaction-grounded parameter estimates. Continuous visual embeddings condition mixture weighting to retrieve and emphasize relevant prior interactions for the current scene region, while a support-aware fusion with a conditional generative prior handles cases with sparse interaction history. The method can incorporate learned embedding refinement to improve retrieval relevance without discretizing the representation.
AI summary
Inference efficiency
Allocate different quantization bit-widths to simultaneously resident KV-cache blocks across multiple agents using an online sensitivity estimate and a shared controller that optimizes under a global memory budget.
AI summary
Training & fine-tuning
Post-train a pathology foundation model with a model-agnostic contrastive objective that explicitly reduces scanner- and stain-specific sensitivity by aligning embeddings of spatially corresponding tissue regions across different acquisition conditions (scanners and stains) while using other regions from the same condition as negatives. Implemented with parameter-efficient LoRA adapters trained on matched multi-scanner and multi-stain whole-slide images.
AI summary
Inference efficiency
Learn a project-specific taxonomy (class boundaries) for a frozen promptable segmenter by fitting a lightweight classification head on top of each image’s generated proposals. The head is trained from the annotator’s labeled examples, then used to classify proposals into the project’s classes, enabling consistent segmentation decisions that match the user-defined taxonomy.
AI summary
Reasoning & planning
A dual-loop safety alignment method that combines an inner introspective risk-analysis loop with an outer meta-learning loop to adapt the introspection policy across diverse jailbreak families. The inner loop performs structured risk analysis, self-assessment, and reflective correction using SI-MCTS, while a dynamic jailbreak simulation module generates increasingly difficult adversarial prompts. The outer loop updates the introspection policy to generalize rapidly to unseen attacks, with continual improvement aimed at changing threat conditions.
AI summary
Multimodal & generation
Image vectorization is often evaluated by rendering fidelity, which cannot distinguish documents that render identically but support different
Source excerpt
Training & fine-tuning
The technique defines an extensible benchmark for fNIRS classification that includes standardized benchmark tasks (cross-subject and within-subject), and a fully automated pipeline from raw data to evaluation to enable reproducible comparison across methods and datasets.
AI summary
Inference efficiency
For flow-based, inversion-free text-guided image editing, introduce a VLM-guided control over the model’s velocity field. Create multiple coupling-controlled velocity candidates, then use a VLM-derived Instruction-Level Similarity (ILS) score to choose the velocity that best matches the editing instruction at each step. Add adaptive spatial masking to preserve regions not intended for change.
AI summary