Recommendation & Information Retrieval - Weekly Roundup

The value of curated, capability-balanced supervision for adapting general language models to educational tasks spanning problem solving, curriculum understanding, and instructional support is demonstrated.

The value of curated, capability-balanced supervision for adapting general language models to educational tasks spanning problem solving, curriculum understanding, and instructional support is demonstrated.

Diagnostics limit explanations based solely on terminal optimization accuracy and distinguish numerical cost from quality, rank coverage and freshness; they establish neither practical-tracker convergence nor predictive or deployment benefits from basis availability.

TriDim, a reusable block that preserves the representation shape and keeps three EEG axes explicit: channel, sample position within each patch, and patch position across the recording, is proposed, a reusable block that preserves the representation shape and keeps three EEG axes explicit.

This method introduces Instance-level Difficulty-Aware Control (IDAC), a reward-shaping mechanism that leverages pre-computed reference statistics (accuracy and token usage) to regulate reasoning depth and enables stable critic-free optimization without learned reward models or online reference-model queries.

WeVisDoc is presented, a two-stage data-centric framework for robust end-to-end document parsing that broadens semantic, structural, and appearance coverage through heterogeneous data and structure-preserving degradation synthesis and guides targeted data construction and reallocation of the target-token budget.

This work introduces ActObs, which also supervises the observation tokens already present in each trajectory, and traces this difference to SFT: action and observation gradients rapidly become orthogonal, while action-only training leaves a large residual observation gradient and degrades environment prediction below the base model.

This work proposes a pure single-loop damped extragradient method with fixed parameters and two new full-gradient evaluations per iteration after one initialization query that attains the optimal condition-number order up to logarithmic factors through fixed explicit updates.

A recursive learning algorithm is proposed that orders SCCs topologically and, for each component, isolates its marginal dynamics and solves a linear system derived from the steady-state moment equations, leveraging parameters recovered for upstream components.

This paper identifies a gap in both speech initiation and response content that requires genuine content understanding and intervention decisions grounded in it and constructs context-matched English monologues in which only the trigger utterance varies within a topic.

This paper presents PART, a unified transformer-based framework for 3D part retrieval and assembly: given a target shape and a part library, PART automatically selects the appropriate parts and predicts their 6-DoF poses to reconstruct the target.

VAST is presented, a V2X/Dynamic Map-aware validation toolchain that connects Scenic, Scenario Simulator v2, AWSIM, Autoware, and SIM-LDM and addresses interoperability challenges, including Lanelet2-to-Scenic mapping, ROS 2-based co-simulation through SS2, Dynamic Map object injection into Autoware, and collection of TTC, PET, collision, timeout, and performance measurements.

Comparisons support complementary benefits of feature-wise gated tactile fusion and training-only predictive supervision of TacSushi, a tactile-grounded, Cosmos3-based world-action policy that learns from recorded future consequences while acting on current observations.

This work introduces LIFD (Look, Imagine, Focus, and Do), a framework for persistent, 3D-aware scene memory that learns a scene-token representation from multi-view agreement and completes it from a single RGB view and recurrent memory.

This work puts the opportunities the compute continuum offers to the test through a real-world multi-view detection model (MvDet) implemented with the FastFL C/C++ high-performance edge inference framework, and obtains up to 1.92x speedup in inference time over a centralised solution using the same devices.

This work finds that the wording of the question affects VLMs in two opposite ways: verbose paraphrasing reduces drift variance by 70--81% on the 8B models and the practical recipe---pad the prompt---further yields measurable gains in accuracy, even under image corruption.

FAMOS, a feed-forward model that predicts movable-part segmentation and joint parameters from a sparse, unordered set of partial point clouds, is presented and a procedural data generator that synthesizes self-annotated assets during training is introduced to overcome the limited scale and diversity of existing datasets.

VA-Bench is introduced to evaluate the complete observe-reason-act-revise loop and tests whether general-purpose MLLMs can turn visual demonstrations and actively acquired evidence into successful embodied action.

Sampling-Guided Policy Search (SGPS), which couples recurring action-target refinement by sampling-based model-predictive control with first-order policy optimization with first-order policy optimization, and shows that refinement improves policy learning beyond initialization and tracking alone.

The propensity of frontier agents to overclaim, a misrepresentation that can mislead the user, is quantified and results show that agents'final responses are not reliable accounts of their actions.

A physics-enhanced machine learning approach for the system identification of Linear Time-Varying systems under time-varying operating conditions in terms of fast-varying natural frequencies and damping ratios by combining a long short-term memory network with an Extended Kalman Filter is proposed.

This work proposes an observer-based dynamic cooperative learning framework incorporating online distributed Gaussian Process (GP) regression, which enables accurate estimation despite incomplete in measurements and deficient GP models, and derives an error upper bound encompassing state estimation and model estimation.

The COMPASS algorithm for OCTSP is introduced, which combines search with learning-accelerated routing by orchestrating parallel sub-solvers and can reach exact solutions in time exponential in cluster size rather than instance size.

Conservative Adaptive Ranking and Screening, Selector-Evaluator Value Assessment, and Dynamic Adaptive Risk-aware Enhancement form CARE-VI, an evidence-regulated target construction framework that preserves the backbone interfaces for critic regression and actor updates.

It is shown that a misaligned model can perform inference engine fingerprinting to determine the specific engine (e.g., vLLM, SGLang) which executes the model, and several ways that inference engines could be changed to make fingerprinting attacks more difficult are discussed.

This investigation provides empirical evidence that FCA-Guided Counterfactual (FCA-CF) framework that uses a Formal Concept Analysis (FCA) concept lattice as a hard structural constraint on counterfactual search, operating over a multi-modal TCGA-BRCA dataset, achieves a clinically important Pareto-dominant outcome.

A global ambiguity set is constructed as the union of admissible mixtures of local ambiguity sets that allows client-specific ambiguity radii and admits a client-wise separable reformulation and establishes a high-probability out-of-sample performance guarantee.

This work demonstrates how rigorous analytical frameworks can address complex humanitarian operations challenges characterised by information asymmetry and limited ground-truth data.

SCGFM-ART, a structure-centric GFM framework that aligns arbitrary graphs onto a shared relational atlas via Amortized Relational Transport, achieves state-of-the-art transferability and establishes coordinate fidelity bounds, prove stability under predicted transport plans, and derive an amortized coverage bound that guarantees the authors' learning objective tightly surrogates ideal relational coverage.

The benchmark, failure-preserving contract, incident provenance, and governance controls needed to prevent infrastructure behavior from being misreported as model behavior and the benchmark, failure-preserving contract, incident provenance, and governance controls needed to prevent infrastructure behavior from being misreported as model behavior are released.

Findings indicate that Federated Learning is a safe and efficient solution to AI-assisted diagnosis in contemporary healthcare when combined with the use of sophisticated object detection models.

It is found that felt ownership depends on the process of collaboration: people disown work when they merely approve AI's suggestions, but retain ownership when they lead, iterate, or rewrite, but retain ownership when they lead, iterate, or rewrite.

RAFT (Retrieval-Augmented Framework for Troubleshooting Agents) is introduced, a stateful RAG framework that abstracts each closed historical case into a directed chain of timeline entries and retrieves at the entry level, surfacing cases whose intermediate states match the active case and returning the parent-case trajectory anchored at the matched state.

LLM-Falsifier is shown to outperform existing falsification tools based on a range of optimization paradigms, from surrogate-based and Bayesian optimization to search-based testing, on 14 of 21 specifications when measured by the average number of simulations required to find a counterexample.

HIL-UMI is introduced, a policy-guided Universal Manipulation Interface (UMI) framework for robot-free human-in-the-loop VLA post-training that preserves the iterative and policy-aware nature of human-in-the-loop learning while decoupling data collection from robot deployment.

SkillAA (Skill Abductive Attribution), a structured skill-optimization framework for frozen language models, represents skill applicability, execution, and composition in a unified graph, allowing the same structure to support skill selection, attribution-guided repair, and update validation.

The semantic action graph is presented, a lightweight domain schema that represents a sports match as performer, action, recipient, moment, and state nodes connected by role, temporal, and outcome edges, providing early evidence that one small, human-readable schema can ground agent generation and support human interpretation at the same time.

This paper introduces the Minimum Span Antibandwidth/Cyclic Antibandwidth Labeling (MSABL/MSCABL) problems and develops a unified Boolean Satisfiability (SAT)-based framework for solving them, and demonstrates the effectiveness of SAT solving as an exact approach for MSABL and MSCABL.

STR-Agent is proposed, an LLM-driven framework for QoS-aware routing in LEO satellite networks that significantly outperforms conventional baselines, and results demonstrate the potential of LLM-driven agent architectures to enable serviceaware and adaptive QoS routing in future LEO satellite networks.

PointEvent is proposed, a lightweight event-wise state-space framework that alternates serialized scans across the complementary orders, progressively consolidating fragmented motion evidence beyond fixed local neighborhoods, and achieves SOTA with the fewest parameters and fastest measured inference among the compared methods.

The value of execution-improved software as a resource for acquiring new policies in this setting is demonstrated, although initial references remain better on two target tasks when averaged across runs.

The results suggest that, for large digital libraries and archives, retrieval accountability and corpus-aware agent design can provide a practical alternative to heavier training-based or graph-construction approaches.

JustMem is introduced, which stores conversation history as compact atomic memories and adapts memory access along two dimensions to each query and achieves the highest mean accuracy and retrieval recall among the compared memory systems while using substantially fewer generative-model tokens for memory construction and inference.

This work formulate state-conditioned minimal sufficient evidence recovery: given a captured agent state, recover a compact evidence combination that supplies the support its next decision still lacks.

KoNeoBench is a benchmark for evaluating LLMs' understanding of Korean neologisms, built on 1,785 Korean neologisms attested in online news since 2020 and curated through expert lexicographic review.

UniPolicy is proposed, an objective-aware multi-policy alignment framework that supports parallel, business-customizable multi-policy beam search, flexibly allocating candidate quotas across objectives under a fixed retrieval budget and outperforming single-objective reinforcement learning and naive reward-fusion baselines.

These cross-lingual transfer experiments show that linguistic proximity has no consistent predictive power for transfer performance, whereas structural similarity in rhetorical organization shows a weak but consistent positive correlation across models, and a set of three methods that explicitly leverage structural information using generative models are proposed.

D-Quant is proposed, a flexible KV cache quantization framework that introduces a Drift mechanism to convert entropy-coded representations of each token into fixed-size bitstreams, enabling regular memory access and parallel dequantization within attention kernels.

This work distinguishes itself from prior work by addressing the novel problem of business semantic layer induction from raw telemetry, operating without labeled training data or manual rule engineering.

This empirical study is an independent reproduction of the dissociation Zhao reported in 2026, where the shape of a large language model's chain-of-thought entropy trajectory predicts whether the final answer is correct, while the magnitude of its total entropy drop does not.

The introduction of AutoData, an agent that searches directly over executable selection algorithms, suggests that data engineering can be treated as an agentic machine learning problem, extending autonomous research from model and training-code optimization to the data.

This work asks what a snapshot misses when the wiring changes over time, and reads three boundaries not usually called schedules: frequency hopping, whose standard results are these closed forms with channels in place of edges; the air gap, whose always-on crossing set is empty and whose known breach came at the one phase a snapshot misses

Mental distance, a loss of belief that the work is worthwhile, is the only symptom unrelated to operational problems, and among posts with a single symptom it is accompanied by a stated intention to leave roughly twice as often as any other.

A lightweight single-probe audit is designed that applies a controlled lengthening intervention under PTIA, and achieves an average detection rate of 85.1% with false-positive rates below 2%.

The paper presents DeltaSelect, an open-source method that identifies tasks whose one-run results consistently track full-benchmark performance using Pearson correlation, maps fractional verifier results to a common score using linear regression, and selects a fixed task set within a dollar budget.

This work introduces a benchmark of 20 real scenes, from coherent streams to violent splashes, captured by seven synchronized, calibrated 4K cameras at 60 fps, with manually refined per-view liquid and container masks and fixed evaluation splits, and presents SplashSplat, built on a single principle: impose physical structure only where the observations can constrain it.

Through a series of worked examples, it is shown how formally representing a theory of mind as a memo-like programming language can lend insight into a variety of theoretical issues in theory-of-mind research.

PaRID combines parallel-aware code transformation with LLM-tuned performance modeling, guided by eight generalizable findings from an offline characterization study, to enable fast soft error detection in parallel applications.

This work introduces FlowSGS, a flow-based posterior sampling method using Split Gibbs Sampling (SGS) to decompose the posterior into a likelihood step and a prior step and provides a form for the prior step that uses SI's reverse-time SDE, and shows connections to previous PnP methods.

Evaluating various models across diverse categories reveals that current models can only maintain short-term consistency that degrades significantly once objects leave the field of view, highlighting the gap between current model capabilities and robust visual memory ("seeing is not remembering"), providing guidance for future development of 4D foundation models.

OmniMimic, a training framework that turns directionally limited animal demonstrations into a single multi-gait policy over target per-axis velocity ranges, and uses a shared actor with soft-gated, gait-specialized residual experts to balance reusable locomotion skills with gait-specific corrections.

Beyond instance-level understanding, few methods have explored fine-grained classification for urban buildings, and thus this work puts forward a fine-grained classification model for urban buildings with a spatially-supervised contrastive loss.

It is revealed that 2D image and 3D shape encoders exhibit largely disjoint failure patterns and rarely share identical wrong labels, whereas two 2D image encoders frequently repeat the same errors, which makes the 2D and 3D pair inherently complementary.

The Active Cross-View Object Geo-Localization (ActiveGeo), where an agent sequentially selects new viewpoints and determines when to stop, aiming to improve localization with minimal observations is introduced, and an ActiveGeo framework with three-stage training is proposed.

Vision-language-action models let robots follow language instructions, but their language backbones of several billion parameters are the main obstacle to running them on robot hardware, and removing 63% of it from OpenVLA-OFT drops LIBERO-Long success from 93.2% to 0.8%.

SProbe, a trailing verification kernel that reads the output of an unmodified vendor GEMM and detects every injected fault across seven fault classes and four matrix sizes, including constructed patterns that TR-ABFT never detects and patterns that a weighted grid code detects but cannot correct.

This work shows that finite-offset log compression causes severe information loss when estimating the Rayleigh scale $\sigma$, which controls diffuse speckle, and validate this theory using synthetic estimation experiments and demonstrate RF-scale recovery on real RF-envelope windows from the OASBUD dataset.

This work introduces a spatial-semantic uncertainty formulation that maintains separate beliefs over each component and integrates probabilistic VLM evidence into a global target-identity posterior, including probability mass for undiscovered targets.

The effectiveness of the YOLOv12-m-seg model for real-time cotton boll detection, segmentation, and selective picking under varying confidence levels is validated.

Results show that, for proximity-defined manipulation hazards, margin selection and fallback strategy can matter more than predicate structure in determining the safety--utility trade-off of a runtime filter.

Results show that the multi-agent design of RoboFind fits the demands of personalized object search, where verifying object identity before declaring completion is what makes the outcome something a user can rely on.

Four-channel bilateral teleoperation removes ambiguity directly by using the leader arm as a separate measurement of the intended equilibrium, making per-axis stiffness identifiable by regression using only the joint-torque sensing already on the manipulator, which is used to fine-tune a VLA to emit stiffness alongside pose.

Frozen transfer to xArm7/MoveIt requires no xArm-specific retraining and candidate-level deployment-feasibility prediction reaches 81.25% recall, 85.20% specificity, and 83.23% balanced accuracy.

RotateIt!, a single-arm framework that uses adaptive axial rotation for dynamic garment unfolding, is presented, to the best of the knowledge, it is the first unfolding framework to employ dynamic axial rotation as its primary manipulation primitive.

This work meta-train speaker-state dynamics through the closed streaming loop, exposing the updater to its own contaminated evidence, and proposes 41k-parameter anchored fast-weights memory, which moves beyond the measured heuristic frontier.

Trie-GRPO, a novel reinforcement learning algorithm based on action prefix trees, which enables step-level advantage estimation, is introduced, which resolves the credit assignment problem by isolating intermediate correct decisions from downstream errors, while effectively balancing exploration efficiency and depth compared to conventional search trees.

HEROIC is a decentralized heterogeneous multi-agent open-vocabulary search coordination framework that requires agents to communicate in natural language only and reaches the target 84% of the time across all 6 scenes, compares to 35-54% for vision-language frontier baselines, frontier-based search, lawnmower, and random-walk running the same perception.

This work considers NAMO in unknown environments revealed through onboard sensing, where the robot must decide whether a blocked route requires relocation or a feasible path may exist through unexplored space, and proposes an online framework that addresses this ambiguity.

This work proposes a three-fold research approach comprising a lossless Binary-Sparse FFT (BS-FFT) and two compression methods: Elastic BS-FFT, which reuses the BS-FFT pipeline on a sampled frequency grid, and density-map-based spatial compression.

Tri-view Consensus-Guided Fusion (TriCGF) is proposed for jointly modeling spectrogram, Mel-frequency cepstral coefficients, and HuBERT representations, outperforming representative SER methods on both datasets.

These findings verify the original paper's claim that User Profile Recommendation achieves competitive performance under its test-set reranking protocol and makes recommendations more transparent.

CoFree (Collapse-Free Reasoning Embedding), a two-stage framework that progressively integrates LLM reasoning into query and document embedding optimization while preserving reasoning quality, is proposed.

SELF-INDEX is proposed, a framework that enables an index to self-evolve without human intervention, and its Optimizer autonomously diagnoses retrieval shortfalls, selectively revises the responsible index keys, and validates each revision before updating the index.

This work presents HOPHY (Hierarchical Off-road Planning using Hypergraphs), a reusable hierarchical terrain representation that organizes map-scale terrain into geometrically connected semantic regions (GSNodes), connectivity-preserving critical regions (Coarse Regions), and typed hyperedges for terrain, agent, and weather context.

In-vivo and ex-vivo experiments validate that LapaTrack-3D provides robust 3D tracking and effectively handles typical challenges such as poor illumination, fast motion, out-of-field-of-view scenarios, partial visibility, and ``organ-background''relative motion.

AMB3R-SLAM achieves strong camera tracking performance across 9 datasets, reducing the absolute trajectory error of previous state-of-the-art methods on VBR and Oxford Spires by over 70%.