Nothing here yet
Coding agents for Lean can produce compiler-passing proofs that do not match the intended theorem or rely on hidden assumptions. Forall-Lean-Agent tackles this by binding verifier results, fresh review, and artifact digests into a traceable acceptance protocol that works with any frontend. The paper evaluates the harness on software-verification and mathematics benchmarks and argues that auditable execution improves correctness guarantees and efficiency, though its empirical claims are stronger on integrity than on controlled performance gains.
Industrial tabular data often suffers from scarcity, class imbalance, and covariate shift between training and deployment. This paper defines the Augmented and Weighted Learning under Covariate Shift (AWL-CS) problem and proposes IGDPR, a framework that steers latent diffusion with invariant potentials and aggregates sample reliability through prototype-based reweighting. The core idea is to synthesize data that aligns with stable decision boundaries rather than outdated source correlations, while filtering out validation noise via structural clusters.
MemFit tackles the high cost of LLM-driven memory consolidation by keeping the LLM out of the write path entirely. It stores each conversational turn verbatim in an append-only store, indexes via BM25 and dense embeddings, and retrieves through a multi-stage pipeline combining lexical matching, dense similarity, pseudo-relevance feedback, and cross-encoder reranking. The work claims state-of-the-art accuracy on three long-term conversational benchmarks while cutting memory construction cost and latency several-fold.
Conceptual database design is difficult to tutor at scale because students iterate on entity–relationship diagrams and need feedback timed to each revision. This paper proposes an educator-guided LLM agent that separates hidden diagnosis of ERD errors from a pedagogical workflow controlling what is disclosed and when. A four-stage scaffold—concept check, guided application, low-detail feedback, and Q&A—was deployed across 383 feedback episodes. The work matters because it trades unrestricted LLM dialogue for educator-governed, artifact-grounded scaffolding that preserves student agency.
Offline goal-conditioned RL (GCRL) struggles with long-horizon tasks because discounting shrinks value differences between distant states until they fall below function approximation error. This work introduces GITA, which learns a single value network conditioned on a temporal abstraction stride $k$ and trains one high-level policy by aggregating advantage-weighted regression updates across multiple scales. By implicitly letting the best-suited scale dominate per state-goal pair, GITA raises average success rate on OGBench by 25 percentage points over HIQL without requiring a problem-specific fixed $k$.
The paper tackles misalignment in canonical Gaussian video representations caused by large global camera motion. The core idea is to precompute frame-wise affine transforms, align all GOP frames into a larger atlas space, and fit canonical Gaussians there before projecting back. This plug-in alignment step lowers the burden on temporal deformation models with essentially no extra parameters, yielding large PSNR gains on high-motion sequences.
Doppelgangers—visually similar yet geometrically distinct surfaces—routinely corrupt structure-from-motion by creating false matches in large image collections. MVDG attacks this bottleneck by repurposing the feed-forward 3D foundation model VGGT to encode arbitrary multi-view image sets in a single forward pass, then applying lightweight per-layer decoders and a confidence-based early-exit gate to classify covisible pairs. The goal is to escape the quadratic $\mathcal{O}(n^2)$ inference cost of pairwise classifiers while preserving downstream reconstruction accuracy.
Post-hoc OOD detectors routinely tune hyperparameters or fit combining rules on held-out samples from the same OOD datasets used for final evaluation. This paper shows that the standard validation protocol only prevents memorization of individual images, not memorization of dataset identity, and that most reported gains vanish when the detector is instead evaluated on truly unseen OOD datasets. The authors isolate the effect with two elegant controls and derive a closed-form expression for the inflation.
NarrativeFlow tackles language-conditioned robot manipulation by generating dense robot velocity fields through a flow-matching formulation, allowing models to train on heterogeneous cross-embodiment data without platform-specific action labels. It introduces a Narrative Delta loss that aligns intermediate representations with textual descriptions of task-relevant scene changes, along with dual subtask tokens to isolate this auxiliary objective from the primary flow-generation path. On standard benchmarks and real-world mobile manipulation tasks with an HSR robot, the method substantially outperforms sparse-keypoint baselines, though absolute success rates and reliance on large MLLM-generated captions leave room for refinement.
Ego2Act introduces a benchmark and automated evaluator for goal-directed egocentric manipulation video generation. It tests whether models can plan and execute multi-step physical tasks from a single starting image and high-level goal, spanning 110 real-world cases. Experiments reveal severe limitations in current video generators, with even the best proprietary model scoring only 64.0 on human evaluation and frequently skipping prerequisite steps or violating physical continuity.
Science teachers need to find documentary clips that illustrate abstract physics concepts like inertia or gravity, but existing retrieval systems only match literal scene descriptions. This paper formalizes concept-to-example video retrieval and proposes CDDA, a three-stage adaptation framework that anchors curriculum concepts between textual examples and sparse visual evidence from documentaries. By structuring the language space on educational texts before transferring to video, CDDA aims to bridge the abstraction gap without destroying concrete image-text alignment, offering a targeted tool for instructional video search.
Logic gate networks replace arithmetic operations with purely Boolean functions for highly efficient inference, yet scaling their width naively causes kernel redundancy and performance saturation. This work identifies that redundancy is most severe at the first gate level and proposes Dynamic Logic Kernel (DLK) and Early-stage Dynamic Logic Kernel (EDLK), which use input-dependent Boolean routing to specialize kernel groups or first-level gate groups. The result is improved kernel diversity and better accuracy-efficiency trade-offs under width scaling, advancing the practicality of discrete logic-based deep learning.
RelationVGGT tackles 3D spatial relation segmentation: given multi-view images, a reference subject mask, and a text relation (e.g., "resting on"), it segments the target object across unposed views without per-scene optimization. The core idea is to replace expensive volumetric relation search with per-pixel relation prediction by fusing semantic DINOv2 features with geometry-aware Pi3 tokens through a subject-conditioned relation transformer. This matters because it moves holistic scene understanding beyond isolated object recognition toward reasoning about how objects are spatially arranged, a capability critical for embodied agents and spatial QA.
Sparse-view 3D reconstruction from only a handful of images is fundamentally ill-posed: standard methods overfit to individual views and leave unseen regions as holes or floaters. HierGF tackles this with a hierarchical 3D Gaussian Splatting pipeline that separates a coarse geometric backbone from a fine-scale field which inherits only spatial means and colors while re-estimating shape and appearance under enhanced pseudo-supervision. Geometry-consistent densification and confidence-weighted diffusion priors are then used to fill gaps and suppress artifacts in under-sampled regions. The authors report strong gains on MipNeRF360, OmniObject3D, LLFF and DTU, alongside a sub-11-minute per-scene reconstruction time on an A100 GPU.
Video benchmarks are supposed to certify that models can understand temporal sequences, yet most can be gamed without watching the video. This paper audits 115 multiple-choice video benchmarks with a five-level attack pyramid that grants attackers access to answer options, question text, other items, single frames, or shuffled videos. After finding severe shortcut vulnerabilities—35 benchmarks break without any visual input and near-duplicates plague 63 of them—the authors screen half a million items down to 840 hardest survivors and compose them into Video-Index, a reproducible meta-benchmark backed by agent-assisted selection and lockfiles.
As video generation scales to minute-long clips, subjects enter and leave the scene, making static-set consistency metrics inadequate. This paper introduces DynSC-Eval, a framework that tracks each subject over its entire visible lifespan and decomposes consistency into local continuity and global identity preservation via six object-level metrics. The authors further derive rewards from these metrics and use DiffusionNFT to post-train video models, demonstrating substantial consistency gains in an autonomous driving testbed and extending them to 30-second generation through curriculum learning.
This paper studies masked diffusion multimodal language models and shows that answer candidates often stabilize retrospectively long before their positions are permanently committed or the rationale-side canvas is filled. The authors introduce two clocks—token stabilization $T_{\mathrm{stab}}$ and commitment $T_{\mathrm{commit}}$—and measure how much of the rationale region $\mathcal{R}$ remains unwritten at stabilization. They pair this with matched-canvas visual-sensitivity ablations and a coverage-accuracy decomposition to explain why prompting changes affect overall accuracy. The analysis matters because it reveals that observing the final rationale alone is insufficient to understand when or how a diffusion model decides its answer.
This paper attacks a growing bottleneck in text-to-image training: how to audit billion-scale recaptioned corpora before spending millions of GPU-hours on downstream training. It proposes a matched-budget audit framework that fixes a text budget $B=64$ and profiles any supervision distribution $D_{\pi,V_c,C}$ across five axes—prompt-side coverage, image-conditioned faithfulness, and caption-surface health—using controllable basic units (CBUs) as a common claim currency. The work matters because it disentangles corpus quality from model-training confounders and releases both a ~490M-caption corpus and a reusable artifact bundle.
Recent video generative models produce stunning visuals but routinely fail at plausible physical interactions and state transitions. This paper proposes a modular synthetic-data pipeline that couples a structured taxonomy with image-editing-based start/end anchors and a novel State-Guided Sampling (SGS) method to smoothly interpolate between them. Fine-tuning a Wan 2.1 model on this curated dataset improves interaction realism, backed by a hybrid VLM-plus-probe evaluator validated against human judgments.
SAM3-ASH tackles fully automated video tracking annotation without any dataset-specific training. Its Generalized Presence Token (GPT) enables SAM3 to process multiple text prompts simultaneously by virtual batching over a single shared image encoding, collapsing per-prompt cost from $\mathcal{O}(N)$ to $\mathcal{O}(1)$. The Annotation and Segmentation Handler (ASH) splits videos of arbitrary length into overlapping temporal chunks and reconciles identities across boundaries via IoU matching, bounding peak GPU memory below 25 GB. Evaluated on eight benchmarks, the pipeline sets a zero-shot HOTA record on MOTS20 and stays within a narrow gap of trained specialists on tasks where mask-based output aligns with the ground-truth format.