Huazhong University of Science and Technology

Video anomaly understanding has long used fixed observation: a model receives a bundle of sampled frames or clustered events and then judges the anomaly, with no way to go back for missing evidence once reasoning starts. SEEK-VAU recasts this as budget-bounded agentic search and verification, letting the policy gather evidence across the precursor, trigger and aftermath stages of an event chain and check sufficiency before closing the case. On its SEEK-Bench, built on a Qwen3-VL-8B backbone, it reaches 55.6 Temporal mIoU, 45.5 QA Accuracy and 43.7 Evidence F1, against 44.2, 37.7 and 28.1 for the fixed-observation Qwen3-VL baseline.

Video anomaly understanding has long used fixed observation: a model receives a bundle of sampled frames or clustered events and then judges the anomaly, with no way to go back for missing evidence once reasoning starts. SEEK-VAU recasts this as budget-bounded agentic search and verification, letting the policy gather evidence across the precursor, trigger and aftermath stages of an event chain and check sufficiency before closing the case. On its SEEK-Bench, built on a Qwen3-VL-8B backbone, it reaches 55.6 Temporal mIoU, 45.5 QA Accuracy and 43.7 Evidence F1, against 44.2, 37.7 and 28.1 for the fixed-observation Qwen3-VL baseline.

Ancient microbial data are scarce and contamination-prone, and a language model left to plan an analysis may cite files that do not exist, apply operations a format forbids, or answer questions the data cannot settle. PaleoRigor confines the model's planner to predefined local modules, validates file references, formats and step dependencies before anything runs, refuses out-of-scope requests with a named reason code, and saves the plan, intermediate files, checksums and decisions. In a preregistered frozen held-out evaluation it passed 23 of 24 runs (95.8%), including all 12 boundary decisions; the same model without the planning contract passed 19.

Ancient microbial data are scarce and contamination-prone, and a language model left to plan an analysis may cite files that do not exist, apply operations a format forbids, or answer questions the data cannot settle. PaleoRigor confines the model's planner to predefined local modules, validates file references, formats and step dependencies before anything runs, refuses out-of-scope requests with a named reason code, and saves the plan, intermediate files, checksums and decisions. In a preregistered frozen held-out evaluation it passed 23 of 24 runs (95.8%), including all 12 boundary decisions; the same model without the planning contract passed 19.

On-policy self-distillation lets one model act as a problem-only student and as a teacher given a reference solution, but the reference pushes the teacher toward short, answer-conditioned derivations that omit exploration and self-correction. TeachBack injects a trailing slice of the reference reasoning as optional working notes and optimizes preferences in both directions: teacher trajectories should win under the problem-only prompt, while student trajectories reshape future privileged teacher rollouts. Across Qwen3-1.7B, 4B and 8B, math averages rise by 4.3, 2.2 and 2.5 points over base, and Knight-and-Knaves averages by 6.1, 3.9 and 7.5 points.

On-policy self-distillation lets one model act as a problem-only student and as a teacher given a reference solution, but the reference pushes the teacher toward short, answer-conditioned derivations that omit exploration and self-correction. TeachBack injects a trailing slice of the reference reasoning as optional working notes and optimizes preferences in both directions: teacher trajectories should win under the problem-only prompt, while student trajectories reshape future privileged teacher rollouts. Across Qwen3-1.7B, 4B and 8B, math averages rise by 4.3, 2.2 and 2.5 points over base, and Knight-and-Knaves averages by 6.1, 3.9 and 7.5 points.

Large vision-language models process hundreds to thousands of visual tokens per image, and inference cost rises with them. Earlier training-free pruning methods ranked all visual tokens by one importance criterion, overlooking that tokens take on different roles as encoding proceeds. BtsPruner locates the role transition from changes in attention concentration, then picks globally referenced representative tokens from later layers and recursively retrieves local detail tokens from earlier layers, preserving both roles under a fixed budget; on LLaVA-1.5-7B it keeps only 32 of 576 visual tokens (5.6%) and retains 91.6% of the dense model's performance.

Large vision-language models process hundreds to thousands of visual tokens per image, and inference cost rises with them. Earlier training-free pruning methods ranked all visual tokens by one importance criterion, overlooking that tokens take on different roles as encoding proceeds. BtsPruner locates the role transition from changes in attention concentration, then picks globally referenced representative tokens from later layers and recursively retrieves local detail tokens from earlier layers, preserving both roles under a fixed budget; on LLaVA-1.5-7B it keeps only 32 of 576 visual tokens (5.6%) and retains 91.6% of the dense model's performance.

Image factuality assessment no longer stops at whether a picture is AI-generated: the EviScene multimodal agent refines its own questions during investigation and reaches 79.05% balanced accuracy and 52.26% evidence sufficiency on 1,527 test images.

Image factuality assessment no longer stops at whether a picture is AI-generated: the EviScene multimodal agent refines its own questions during investigation and reaches 79.05% balanced accuracy and 52.26% evidence sufficiency on 1,527 test images.

Linux readahead infers the next page from recent file offsets, which fails when accesses follow workload structure such as sparse startup reads, B-tree key-order traversal, or tensor-layout model loading. PredictIO separates prediction from execution: the kernel delivers observed accesses and application hints to user-space policies, which emit uniform page-range requests that a kernel backend validates, bounds, and issues as asynchronous prefetch I/O. Across application launch, SQLite range scans, and llama.cpp model loading, latency drops by 5.3–26.3%, scans speed up by up to 2.99, and model loading drops by 8.8–47.9%.

Linux readahead infers the next page from recent file offsets, which fails when accesses follow workload structure such as sparse startup reads, B-tree key-order traversal, or tensor-layout model loading. PredictIO separates prediction from execution: the kernel delivers observed accesses and application hints to user-space policies, which emit uniform page-range requests that a kernel backend validates, bounds, and issues as asynchronous prefetch I/O. Across application launch, SQLite range scans, and llama.cpp model loading, latency drops by 5.3–26.3%, scans speed up by up to 2.99, and model loading drops by 8.8–47.9%.

A multi-axis open-coding study of 200 CyberGym traces found that code localization and understanding (43.1%) plus vulnerability reasoning and trigger design (17.3%) account for 60.4% of tokens and that only 24.4% of matched comparisons preserve success at lower total cost; the authors then present AVRI, an interface built on a persistent Bidirectional Evidence Trace (BET), which on 20 evaluation tasks reduces total cost by 18.0% for Codex and 23.7% for OpenCode while preserving success and improving or maintaining recall.

A multi-axis open-coding study of 200 CyberGym traces found that code localization and understanding (43.1%) plus vulnerability reasoning and trigger design (17.3%) account for 60.4% of tokens and that only 24.4% of matched comparisons preserve success at lower total cost; the authors then present AVRI, an interface built on a persistent Bidirectional Evidence Trace (BET), which on 20 evaluation tasks reduces total cost by 18.0% for Codex and 23.7% for OpenCode while preserving success and improving or maintaining recall.