Optimization
-
Direct Pass@$k$ Optimization for Thought Pruning: Balancing Quality and Diversity in Test-Time Reasoning
2026-10-22 17:59:48Mahdi Salmani, Adel Javanmard, Devansh Gupta, Meisam RazaviyaynAbstract
Test-time scaling has emerged as a key inference strategy for reasoning models, where a model generates a large number of candidate solutions in the hope of finding at least one correct solution. Running all candidate solutions to completion can be computationally demanding, so recent work prunes the candidate pool after generating only a short prefix, committing further computation only to the surviving candidates. Existing pruning strategies divide broadly into two categories: Quality-based methods assign a score to each partial solution and discard those predicted to ultimately lead to an incorrect final solution, while diversity-based methods select partial solutions that follow different reasoning trajectories and are therefore likely to cover different final solutions. The tension between these two objectives is an instance of exploration versus exploitation, yet little to no prior work on pruning exposes this trade-off directly, let alone optimizes it. In this paper, we introduce a pruning procedure that addresses this trade-off directly by optimizing pass@$k$ over the selected solution pool. In particular, it chooses the pool to maximize the probability that at least one of its partial solutions, when continued to completion, yields a correct answer. Because this objective simultaneously rewards high-quality partial solutions and penalizes redundancy among them, quality and diversity are naturally balanced by the criterion itself rather than through separate ad-hoc design choices. On eight open-weight reasoning models, our method outperforms existing quality-based and diversity-based pruning strategies. The gains are particularly pronounced when the pruning procedure keeps a moderate number of partial solutions for continued generation, highlighting the value of directly balancing quality and diversity during pruning.
Abstract (translated)
URL
https://arxiv.org/abs/2610.31667
PDF
-
SpectralCanary: Embarrassingly Simple Low-Frequency Traces for T2I Dataset-Use Auditing
2026-10-22 17:59:03Sy-Tuyen Ho, Anirudh Satheesh, Soham Chawathe, Huy Nghiem, Yongkyun Lee, Andrew Adams Schoen, Furong HuangAbstract
Auditing whether a text-to-image (T2I) model was fine-tuned on a particular image collection is difficult: a model can absorb collection-level visual characteristics without reproducing training images. Proactive dataset-use auditing plants a shared signal in a dataset before release, then later checks whether that signal appears in a suspect model's generated outputs. Existing approaches often trade off verifiability, fidelity, robustness, and deployability. We introduce $\textbf{SpectralCanary}$, which uses a smooth low-pass mask to blend a fixed canary image into every collection image while leaving captions unchanged and requiring neither auxiliary generation nor per-image optimization. A lightweight verifier detects the transferred signal in suspect-model outputs. Across eight tests on the Pokemon dataset and three realistic data transformations, spanning two architectures families, SpectralCanary achieves the highest average per-generation TPR@$1\%$ FPR ($91.1\%$) and fixed threshold model-level accuracy using 30 generations ($94.8\%$) among the evaluated methods. Across five datasets spanning artistic, medical, satellite, and fashion domains with SD3.5, SpectralCanary averages $92.4\%$ per-generation TPR@$1\%$ FPR while preserving the released images (SSIM $0.989$, LPIPS $0.022$) with a near-zero mean change FID (mean $\Delta$FID $0.05$) across datasets. Matched-energy ablations on Pokemon and ROCOv2 support our design choice, low-frequency placement transfers more reliably compared to mid/high-frequency placement. Under the evaluated adaptive attacks, the most effective removal requires aggressive modification and incurs more than $25$ $\Delta$FID points. These results identify low-frequency visual signals as effective carriers for collection-level T2I audit traces.
Abstract (translated)
URL
https://arxiv.org/abs/2610.31659
PDF
-
HiP3R: Hierarchical Pose Graphs for Long-Horizon 3D Reconstruction
2026-10-22 17:51:10Zunnan Xu, Shangchen Zhou, Yihang Luo, Chen Change LoyAbstract
Feed-forward models accurately estimate camera motion and 3D geometry from short video windows. However, computational and memory costs prevent direct inference on sequences containing thousands of frames. Long videos must therefore be processed as overlapping chunks. This division produces independent local reconstructions with inconsistent coordinate frames and duplicate estimates of shared cameras. Achieving global consistency requires propagating constraints from adjacent overlaps and distant revisits across the sequence. This requirement naturally motivates pose graph optimization. However, the choice of graph level creates a trade-off. Chunk-level graphs efficiently resolve scale drift and close large loops. Yet, their rigid transformations cannot correct internal errors or conflicting frame predictions. Conversely, frame-level optimization offers local flexibility, but scaling it globally is computationally expensive and can break metric scale. HiP3R resolves this trade-off using a hierarchical pose graph. HiP3R first optimizes a robust chunk-level $\mathrm{Sim}(3)$ graph to establish the global layout and scale. It then holds this layout fixed and estimates one shared $\mathrm{SE}(3)$ camera per frame, turning overlapping window predictions into a single trajectory. Experiments across multiple benchmarks demonstrate the effectiveness of HiP3R in improving camera trajectories and 3D reconstruction. Our method applies to both chunk-based and streaming backends without additional training or fine-tuning. The codes are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.31635
PDF
-
DiffDreamer: Coupling World Models with Differentiable Simulation for Agile Quadrotor Control
2026-10-22 17:41:13Fanxing Li, Yuxiang Huang, Shengyang Wang, Fangyu Sun, Shuyu Wu, Tianbao Zhang, Dexin Zuo, Yan Yufei, Danping Zou, Wenxian YuAbstract
Tasks such as quadrotor dynamic-gate racing require agents to anticipate external motion while maintaining precise high-frequency control. World-model-based reinforcement learning provides a natural solution by learning latent dynamics for future imagination, yet it often entangles environmental evolution and the robot's own dynamics in a single learned rollout, where model bias can affect policy optimization efficiency. We propose DiffDreamer, a differentiable reinforcement learning framework that tightly couples a learned world model with differentiable simulation for actor optimization. In one optimization step, the learned world model propagates latent states that capture external dynamics and history-dependent features, while the differentiable simulator propagates the robot's explicit physical state. We further decompose the actor objective into a critic-driven pathway for non-differentiable task rewards and a simulator-driven pathway for differentiable motion rewards. Experiments on aggressive tracking and dynamic-gate racing show that DiffDreamer improves training convergence over the model-free, model-based, and differentiable-RL baselines, and final performance over these baselines and classical planning and control methods. Additional experiments assess reward decomposition and the odometry-conditioned relative-state representation through ablations. We also provide proof-of-concept real-world flight experiments for validation.
Abstract (translated)
URL
https://arxiv.org/abs/2610.31617
PDF
-
Decentralized Bi-Level Optimization for Cooperative Orbital Transportation of a Rigid Payload
2026-10-22 17:05:17Sidhdharth D. Sikka, Revathy Ravuri, Hei Yin Jowett Chan, Tim Echtermeyer, Shaoshuai MouAbstract
The rapid growth of the space economy, alongside increasing orbital congestion and debris, is driving demand for reliable on-orbit transportation of large and non-cooperative objects. Performing such transportation with a swarm of small spacecraft distributes risk and removes the single point of failure inherent to monolithic architectures, but requires solving a non-convex trajectory optimization coupling every agent's cone-constrained thrust to the payload's rotational dynamics. Existing approaches span decentralized control laws with asymptotic guarantees but limited constraint enforcement, and centralized and partially centralized planners that reintroduce a single point of failure. In this work, we present a decentralized bi-level framework driven by exact gradients: the problem is split into an inner convex thrust allocation and an outer search over payload torque trajectories. This decomposition yields fuel-efficient solutions quickly, without requiring full NLP convergence, and at short timescales its performance scales with the number of agents. Theoretical convergence guarantees are established, and the method is validated through extensive Monte Carlo simulation, including closed-loop recovery from in-flight faults. These properties make the framework well suited to spacecraft swarm applications.
Abstract (translated)
URL
https://arxiv.org/abs/2610.31562
PDF
-
Diffusion Language Models for Perplexity-Aware Black-Box Attacks
2026-10-22 17:00:39Ali Al-Lawati, Elsayed Eshra, Dongwon Lee, Suhang WangAbstract
\emph{Continuous-space} attacks find prompts that trigger malicious behaviors, such as overthinking, in black-box LLMs by sampling or optimizing over a low-dimensional Gaussian latent space and decoding it to text through a \emph{random mapping} and nearest-token lookup. Because the random mapping is not learned from language, its prompts can be highly unnatural, and as such easily detectable through input guardrails, and the risk estimates they yield are not grounded in natural prompts. In this paper, we demonstrate that the same continuous latent-space framework can be coupled directly to a learned generative distribution over language, a continuous diffusion language model (dLLM), which removes the artificial random mapping while preserving the standard-Gaussian latent formulation and the downstream sampling or optimization procedure. We evaluate this approach under two settings: sampling-based estimation using \emph{RareTrap} and optimization-based search using \emph{ThinkTrap}. We find that character-level perplexity drops from $10^3$--$10^7$ to 3--5 in RareTrap and from 20--28 to 4.3--5.4 in ThinkTrap. We also find that model risk estimates can differ by an order of magnitude across the two mappings.
Abstract (translated)
URL
https://arxiv.org/abs/2610.31558
PDF
-
SQuAT: Spherical Lattice Vector Quantization-Aware Training
2026-10-22 15:14:44Sebastian Loeschcke, Ivan Koryakovskiy, Tycho F. A. van der Ouderaa, Riccardo Del Chiaro, Mart van Baalen, Paul N. Whatmough, Markus NagelAbstract
Vector quantization (VQ), in particular lattice-based methods, offer strong rate-distortion trade-offs for low-bit large language models (LLMs), yet their behavior under quantization-aware training (VQ-QAT) remains poorly understood. We scale lattice VQ-QAT to billion-parameter LLMs and multi-billion-token training regimes, and introduce SQuAT, a shape-gain VQ-QAT approach trained with a separate straight-through estimator (STE) for the shape and gain. SQuAT decomposes weights into direction and magnitude: normalized directions are quantized using an $E_8$-derived spherical codebook, while gains are quantized independently with low-bit scalar quantizers. We show that, unlike a standard STE applied to the full quantizer, which ignores the shape-gain structure, these separate STEs induce tangent-space updates for directions, yielding an implicit form of spherical (Riemannian) optimization. To enable scalability, we develop a distributed exact nearest-neighbor assignment scheme, in which workers quantize disjoint weight blocks and communicate only discrete indices, reducing VQ-QAT training time by 12.8$\times$ and allowing us to scale it to 10B tokens. Across instruction-tuned LLaMA-3.2-1B/3B, Qwen3-4B, and base Qwen3-1.7B, SQuAT consistently outperforms standard VQ-QAT STE under identical quantizers and initialization, and achieves SOTA VQ-QAT accuracy.
Abstract (translated)
URL
https://arxiv.org/abs/2610.31412
PDF
-
Memory-Aware Reward Modeling: Learning Human Preferences for LLM Memory Use
2026-10-22 13:43:33Yijiang River Dong, Zexue He, Cheng Yu, Tiancheng Hu, Michael J Ryan, Jan Batzner, Zheng Hui, Shaolong Wu, Orestis Papakyriakopoulos, Alex Pentland, Nigel Collier, Jiaxin PeiAbstract
Memory enables language model assistants to maintain continuity across sessions and generate personalized responses, but knowing more about a user does not necessarily produce responses they prefer. Existing evaluations assess memory capabilities without directly establishing whether memory use benefits the user. To study this gap, we collect approximately 1,000 pairwise judgments from 87 participants using their own ChatGPT queries and personal memories. We find that memory-conditioned responses are not consistently preferred over responses generated without memory and in some cases, users strongly prefer the latter. Automatic evaluators also show limited agreement with users and favor memory-conditioned responses substantially more often than users do. Motivated by these gaps, we introduce a memory-aware reward model that learns from user judgments, achieving 72.8\% preference prediction accuracy and outperforming the existing baselines. Our findings motivate evaluation and optimization objectives that align memory use with the preferences of the people whose information is being used.
Abstract (translated)
URL
https://arxiv.org/abs/2610.31272
PDF
-
Is the Judge Its Twin? Post-training makes a model's writing more predictable but barely moves its taste, as a judge, toward predictable writing
Abstract
Language models now routinely grade other language models. If post-training makes a model's writing more predictable, it may also teach the same model, as a judge, to reward predictable writing. We test this directly. We follow two open 7-billion-parameter model families, OLMo-2 and Zephyr, from their base models through supervised fine-tuning (SFT) and direct preference optimization (DPO), and measure every stage as a writer of short stories and as a judge of story pairs. As writers, the models drift as feared. Each family's trained model finds its stages' stories more familiar in the order base, SFT, DPO, in all ten prompts, and a model from the other family finds the trained stories 7.0 to 9.2 percent (OLMo-2) and 24 to 25 percent (Zephyr) less surprising per token. As judges, they barely move toward predictable writing. Asked which story is better, a question every judge passes a competence check on, no trained judge's preference for the more predictable story grows by as much as one point of pick probability at its estimate. A one-sided 95% upper bound on that growth is about 5 points on the widest pairs. Training instead makes judges more swayed by story length and by display order, and it breaks "more creative" as a question. Trained judges no longer reliably prefer a story to its own words in scrambled order. For these two families, the practical hazard in a small trained judge of creative writing lies in these measurable habits.
Abstract (translated)
URL
https://arxiv.org/abs/2609.32196
PDF
-
What Pairwise Evaluation Misses: Reward Scores across Prompts
Abstract
Reward models score responses for preference optimization, filtering and ranking, and pooling scores across prompts needs them to be comparable. Yet pairwise evaluation compares two responses to the same prompt, so any score component shared by a prompt's responses cancels and goes untested. We study this component by comparing between-prompt variation in model scores with the same variation in human ratings of the same responses. We propose a human-referenced audit, built from a between-prompt variance share, a sibling-rating regression and prompt substitutions, and apply it to eighteen released scorers and six matched training conditions. We find that scores cluster by prompt more than the ratings do: on HelpSteer2, six reward models have between-prompt shares of 0.34 to 0.64 against a human share near zero. Replacing the original prompt with a fixed instruction keeps substantial clustering but weakens agreement with prompt-level human ratings, so clustering alone does not show agreement with humans. Part of that variation is useful: subtracting prompt means lowers the helpfulness of globally selected responses, and scores stay sensitive to a wrong prompt even when training shuffles prompt means. We propose that reward evaluation check between-prompt variation, sensitivity to a wrong prompt and usefulness for selection separately.
Abstract (translated)
URL
https://arxiv.org/abs/2610.31090
PDF
-
SCOPE: Compiling Natural-Language Policies into Neurosymbolic Predicate Programs
2026-10-22 10:41:13Arnon Mazza, Elad LeviAbstract
Policy enforcement for LLM agents has shifted from single-turn content moderation to compound, application-specific policies evaluated over multi-turn transcripts and tool-call trajectories. Fine-tuned guardrail models are efficient but degrade on compound policies, and while LLM-as-a-judge approaches achieve higher accuracy, they incur high inference cost and tend to produce unstable predictions. Neurosymbolic methods offer a natural alternative, decomposing the policy into narrow neural decisions composed under explicit logic. However, existing symbolic layers lack the required expressiveness and are optimized against fixed data rather than the policy itself. To address this, we introduce SCOPE, which compiles a policy into an executable program of neural predicates executed by small models, deterministic extractors, and code that composes their outputs. The program is optimized jointly with its training data, using adversarial generation of counterexamples that target where the program deviates from the policy. We evaluate SCOPE on a benchmark of real-world policy tasks against prompt optimization, task decomposition, and workflow generation methods, achieving the highest average accuracy across tasks and models. Programs optimized with the weakest executor transfer to other models without further optimization. This allows them to be deployed in production on inexpensive models, where they reach accuracy comparable to frontier reasoning models. Unlike these monolithic models, SCOPE produces substantially more stable predictions, and each verdict is interpretable through the predicate outputs that produced it. Additionally, we validate the key components of our method through an ablation study. SCOPE thus enables reliable, interpretable, and efficient policy enforcement at production scale.
Abstract (translated)
URL
https://arxiv.org/abs/2610.31062
PDF
-
ReflectPO: Reflection-Guided Policy Optimization for Long-Horizon LLM Agents
2026-10-22 08:54:24Rumei Li, Xunliang CaiAbstract
With external tools, large language models (LLMs) can tackle complex tasks through sustained environmental interaction. LLM-based agents are therefore increasingly used to tackle complex long-horizon tasks in real-world environments. However, these tasks involve sequential, interdependent decisions and changes in environmental states. Early execution errors affect subsequent interaction histories and environmental states, and their effects accumulate along the decision chain. To address this challenge, we propose Reflection-Guided Policy Optimization (ReflectPO), a reinforcement learning framework for autonomous error recovery in long-horizon tasks. ReflectPO comprises two core components. The first is Reflection-Guided Sampling. We use branch differences and repeated visits in interaction trajectories to construct hints for error recovery. The second is Tree-Structured Credit Assignment. We organize sampled trajectories into trees and assign action-level credit using parent--child reward differences and recovery gains. Experiments over two long-horizon tool-use benchmarks show that ReflectPO outperforms multiple existing baselines in most domains. It also achieves the best overall performance on average. Further analyses show that ReflectPO effectively improves agents' ability to recognize their own deviations, recover from erroneous states, and continue making progress toward task completion.
Abstract (translated)
URL
https://arxiv.org/abs/2610.30933
PDF
-
H-2DGS: Height-Field Gaussian Splatting for Sharp and Deformable Neurosurgical Surface Reconstruction
2026-10-22 08:33:14Zhang Zichuan, Bart Brouwers, Rembrandt Bakker, Maud Landers, Geert-Jan Rutten, Maxime ChamberlandAbstract
Neurosurgical navigation commonly presents magnetic resonance imaging (MRI) as 2D slices, making it difficult to relate the anatomy in those slices to the cortical surface observed through the surgical microscope. We seek a common 3D visualization that combines a photorealistic reconstruction of the exposed cortex during tumor surgery with whole-brain MRI context and diffusion tractography pathways. This requires the reconstructed cortex to form a clear boundary around the brain anatomy rather than a diffuse volume that obscures internal structures. Conventional 3D Gaussian Splatting (3DGS) can reproduce observed views but, under limited surgical view coverage, may distribute opacity through a thick and geometrically ambiguous band. We introduce height-field 2D Gaussian Splatting (H-2DGS), a three-stage pipeline that concentrates a robust 3DGS reconstruction, fuses its depth into a shared truncated signed distance field (TSDF) surface, and represents that surface with curved, surface-oriented Gaussian primitives. Separate height, color, and opacity bases provide local geometry and appearance, while a neighbor-transition objective coordinates overlapping patches. The explicit surface further supports postoperative alignment: MRI-derived depth deforms the reconstruction, and tracked-color supervision with alternating optimization preserves its appearance. Across five real neurosurgical cases, H-2DGS gives low multi-view depth inconsistency, a compact 7.97MB representation, and interactive rendering at 29--42ms per frame. The resulting sharp, deformable surface integrates clearly with tractography and MRI anatomy, including a postoperative resection cavity.
Abstract (translated)
URL
https://arxiv.org/abs/2610.30910
PDF
-
HimmBO: High-Dimensional Interactive Model-Merging Bayesian Optimization for Image Generation
2026-10-22 07:56:10Jinyuan Mao, Zhihao Shen, Chenxi LiuAbstract
Fine-tuning has become a common way to customize text-to-image models, leading to community collections of over 100K lightweight adapters. Adapters sharing a base model can be merged with continuous coefficients. This turns a large collection into a high-dimensional continuous design space, which recent work explores interactively using preferential Bayesian optimization (PBO). However, existing approaches are limited to a few dozen preselected adapters and require expensive image generation in every interaction round. We introduce HimmBO, a two-stage method that scales preference-driven adapter merging to much larger collections while reducing image-generation cost. Its screening stage recovers the active adapter set through level-set estimation over pre-generated images, requiring no image generation. The refinement stage then optimizes merge coefficients in the recovered low-dimensional subspace. Both stages use a style-aware kernel, allowing preference information to transfer between visually similar adapters. In simulated-user image-matching experiments, HimmBO achieves higher final similarity than all comparisons while reaching a given similarity with under one tenth of the image generations required by prior work. Its performance remains stable as the collection grows to 1080 adapters, while competing methods degrade substantially.
Abstract (translated)
URL
https://arxiv.org/abs/2610.30875
PDF
-
Synthetic-to-Real Code-Switched ASR: A Spontaneous Nepali-English Podcast Benchmark
2026-10-22 07:41:21Firoj PaudelAbstract
Nepali-English code-switched conversational speech presents severe challenges for automatic speech recognition (ASR), chiefly through script confusion (inappropriate mixing of Devanagari and Latin orthography) and elevated error rates at language switch points. Supervised fine-tuning (SFT) can adapt multilingual foundation models, but human code-switched audio is expensive to collect and annotate. We curate a new benchmark of 13,044 spontaneous podcast utterances (15.45 h total; 10,214 test, 2,830 dev), audited and verified to eliminate machine translation leakages and acoustic loops. We investigate a two-stage synthetic-to-real adaptation framework: Stage 1 applies SFT on 0.95 h of speech synthesized via a multi-speaker, dual-engine TTS pipeline; Stage 2 explores Group Relative Policy Optimization (GRPO) with transcription and script rewards. We find that synthetic SFT provides the primary cross-domain transfer to spontaneous human speech, reducing Mixed Error Rate (MER) from 23.40% to 21.52% (-1.88 pp) and switch-point error rate (SPER) from 35.89% to 28.77% (-7.12 pp). Subsequent GRPO yields small, statistically significant adjustments on 173 test utterances (1.69%), driving English script confusion (SCR_en) from 6.45% to 6.36% (p <= 0.001) and SPER to 28.70% (p = 0.022 clustered). Crucially, ablation reveals that in this SFT-converged encoder-decoder setting, an auxiliary script reward term yields performance identical to MER-only optimization because rollout candidate groups exhibit near-zero script variance on synthetic data. On monolingual benchmarks, SFT improves Nepali MER by 2.71 pp (stabilizing at 18.42% after GRPO, a 2.38 pp gain over baseline) while preserving English lexical WER (3.38% vs. 3.33%). Verified transcripts, timestamps, episode metadata, and reconstruction scripts are publicly released.
Abstract (translated)
URL
https://arxiv.org/abs/2610.30860
PDF
-
Parallelizable Probabilistic Latent Reasoning for Diverse Reasoning Trajectories
2026-10-22 07:41:12Seokhyun Lee, Seongjun Lee, Changhee LeeAbstract
Language models relying on verbalized Chain-of-Thought (CoT) are constrained to token-by-token generation in the language space, where many tokens serve textual coherence rather than core reasoning. This entangles genuine differences in logical trajectories with superficial variations in verbalization. Moving reasoning into a compact, continuous latent space offers a promising alternative for efficiently representing and exploring diverse reasoning trajectories. However, current latent models remain largely deterministic, capturing only a single reasoning trajectory rather than modeling a distribution over multiple valid alternatives. While stochastic approaches parameterize distributions over latent reasoning steps, they frequently suffer from unstable optimization and limited empirical performance. Furthermore, their reliance on autoregressive latent prediction during training precludes effective parallelization, leading to prohibitively long training times. To overcome these bottlenecks, we propose Probabilistic Latent Reasoning Models (PLRM), a parallelizable variational framework for probabilistic latent reasoning. PLRM adopts a JEPA-style objective in which the posterior infers latent distributions in parallel from observed reasoning trajectories, while the prior learns to predict the subsequent latent distribution via teacher forcing. To model heterogeneous reasoning processes, we introduce a discrete strategy variable together with a mixture-based prior, allowing the model to preserve the Gaussian-mixture structure induced by multiple distinct reasoning trajectories rather than collapsing them into a single Gaussian. Across diverse benchmarks, PLRM achieves performance competitive with deterministic latent reasoning models on single-trajectory datasets while enabling efficient training and consistently outperforming competing stochastic baselines on multi-trajectory datasets.
Abstract (translated)
URL
https://arxiv.org/abs/2610.29385
PDF
-
One Evaluation Is Enough: Inversion-Free Image Editing with Trajectory Correction
2026-10-22 06:56:18Lifan Jiang, Taiyang Chen, Senlin cheng, Bolei Xu, Xiaobo Li, Can Ye, Dehai Zhao, Deng Cai, Boxi WuAbstract
Real-image editing commonly relies on inversion and iterative sampling, while efficient one-step editors often stabilize a large update by estimating and averaging editing fields at multiple noise levels. We ask a stricter question: is a single temporal field evaluation sufficient for reliable inversion-free editing? Our answer rests on a previously underused duality in a variance-preserving (VP) one-step model: one source-target query at a shared noisy state simultaneously determines a local angular semantic tangent and a clean endpoint displacement. We integrate the tangent over the analytically known remaining VP angle to obtain a nominal one-step transport, and use the endpoint displacement to correct its long-horizon extrapolation through a constrained projection. This transport-first, correction-second construction yields Endpoint-Calibrated Transport (ECT), a closed-form, training-free editor requiring only one noise level, two text conditions packed into one denoiser batch, and one latent update. ECT requires no image inversion, trajectory integration, second temporal observation, or iterative optimization, and can be directly applied to pretrained epsilon-prediction VP one-step generators. Across the reported benchmark settings, ECT delivers stable gains in editing quality within an extremely short editing time.
Abstract (translated)
URL
https://arxiv.org/abs/2610.30827
PDF
-
Beyond Recall Saturation: Scaling Hard-Negative Reranker Training for Industrial Legal Retrieval
2026-10-22 04:11:50Yunhan Li, Mingjie Xie, Zeyang Shi, Gengshen Wu, Min YangAbstract
Industrial retrieval systems often improve quality by enlarging embedding candidate pools or adopting complex training pipelines. We show that, under a sufficiently large but practical candidate pool, embedding recall exhibits diminishing returns, motivating a closer examination of reranker quality. On Chinese legal retrieval benchmarks, embedding top-300 reaches a high-recall operating region, while relevant evidence may still be ranked below the output cutoff. We compare hard-negative strategies for reranker training, including embedding-mined, self-mined, and dynamic-negative variants, under aligned retrieval protocols that evaluate reranking after candidate retrieval. Among the evaluated staged configurations, an embedding-to-self-mined pipeline provides a favorable trade-off; additional dynamic stages do not improve all held-out metrics. The selected pipeline scales from a 0.6B to a 4B reranker. Relative to the native 4B reranker, the trained 4B Stage2 model improves reported metrics on the STARD and CSAID benchmarks and on an internal development set, and is preferred in 72.4\% of non-tied comparisons on 410 de-identified, reconstructed internal operational-query inputs in a latency-sensitive offline preference evaluation. These results support evaluating the retrieval and reranking stages separately when selecting an optimization target for industrial retrieval systems.
Abstract (translated)
URL
https://arxiv.org/abs/2610.24478
PDF
-
AgentDreamer: Agentic 3D Motion Reasoning for Text-Controllable Physics Simulation
2026-10-22 03:46:22Mijeong Kim, Suho Park, Junha Park, Bohyung HanAbstract
We propose AgentDreamer, an agent-guided optimization framework that aligns text instructions with simulated motion through explicit 3D motion planning. Given a text instruction and scene geometry, an off-the-shelf agent translates the instruction into a structured semantic motion prior, specifying what should move, in which direction, and in what temporal order. The agent represents this prior using parametric functions over a series of temporal chunks, yielding dense 3D trajectories. We then optimize the parameters of a differentiable MPM simulator such that its rollout best matches the prior while remaining constrained by the scene dynamics. This allows the agent to provide semantic guidance from language, while the simulator grounds it in physically feasible motion. We further introduce Motion-IG, an information-theoretic metric for text-motion alignment based on masked text recovery. By comparing the likelihood of recovering masked motion-related content with and without the simulated motion, Motion-IG measures the information contributed by the motion beyond that available from the remaining text and scene context. Experiments show that AgentDreamer improves text alignment over video-based guidance, producing simulations that more closely follow the requested physical behavior.
Abstract (translated)
URL
https://arxiv.org/abs/2610.30679
PDF
-
Asking Less, Adapting Better: Feedback-Efficient Test-Time Adaptation for Vision-and-Language Navigation
2026-10-22 03:05:25Zixu Wang, Huaquan Zhang, Shoukai Xu, Jinwu Hu, Zhiquan Wen, Mingkui TanAbstract
Vision-and-Language Navigation (VLN) requires agents to follow instructions and navigate to target locations. However, current VLN agents often suffer severe performance degradation in unseen environments due to distribution shifts. Test-Time Adaptation (TTA) offers a promising paradigm to bridge this gap, yet existing methods that rely on unsupervised entropy minimization can propagate errors through the trajectory, causing cascading failures in navigation. Recent methods mitigate this by incorporating human feedback, but they apply trajectory-level supervision uniformly across all steps without localizing the actions is truly informative, leading to inefficient feedback utilization and mismatched optimization granularity. To address these limitations, we propose FETA, a Feedback-Efficient Test-Time Adaptation method that improves both feedback efficiency and optimization reliability. To reduce unnecessary human interventions, we introduce a hierarchical sample selection strategy to localize informative samples. Specifically, we first filter trajectories whose normalized policy entropy exhibits large fluctuations. Within each selected trajectory, we further select the critical action via an entropy-gradient saliency criterion and query a single binary feedback on its correctness. A discrepancy-aware entropy optimization objective then updates the policy only at the queried step, with adaptive scaling that assigns larger relative weights to samples with greater prediction-feedback discrepancy. Extensive experiments across multiple benchmarks demonstrate that FETA achieves state-of-the-art performance with fewer human interventions, while remaining robust under noisy feedback and continual adaptation settings.
Abstract (translated)
URL
https://arxiv.org/abs/2610.30643
PDF
