Papers

We address the challenge of syntactic parsing for Urdu, a morphologically rich language, and present state-of-the-art results for both constituency and dependency parsing. This paper offers four major contributions: 1) the conversion of the CLE-UTB phrase structure treebank into a dependency treebank by developing language-specific head-word and phrase-to-dependency label mapping rules; 2) a novel sequence labeling scheme that transforms the parsing task into a unified representation; 3) the training of contextualized word representations on a large 220 million tokens Urdu corpus collected from the web; and 4) development of parsing framework using two learning paradigms, single-task and multi-task learning. Several post-processing rules are applied to improve the quality of the automatically converted dependency structure treebank. The proposed sequence labeling scheme enables the use of a shared architecture that learns the syntactic structures from both grammatical structures simultaneously and hence improves generalization. Experiments show that the multi-task learning setup significantly enhances parsing performance, achieving an F1 score of 91.39 for constituency parsing (an improvement of 3.29 points) and a labeled attachment score of 85.69 for dependency parsing (an improvement of 1.49 points). These results demonstrate that learning cross-task representations provides measurable benefits and advances the state of syntactic parsing for Urdu.

Behavioural biometric templates are widely believed to degrade as the gap between enrolment and verification grows, but few studies measure this template ageing effect directly under controlled conditions. We collected a longitudinal dataset of 40 fixed passwords, each typed four times per weekly session over eight consecutive weeks. We compare a scaled-Manhattan matcher (M1), a gradient-boosted classifier (M2), a TypeNet-style recurrent embedding model (M3), and a TypeFormer-style Transformer (M4) under a 5-fold subject-disjoint protocol and a design that jointly varies mechanism and the enrolment-to-query gap, from 0 to 7 weeks. Template ageing proves large and systematic. Error increases monotonically with the gap for every mechanism, from an EER of 14.6-27.2% at a gap of zero to 25.5-37.1% at seven weeks, or 1.7% of decision error per week elapsed (p < 0.001). However, the choice of mechanism matters more than its rate of ageing. Baseline accuracy spans 12.6 percentage points across the four mechanisms, the degradation each accumulates over seven weeks spans only 2.3 points, and ageing never reorders them. A matcher can therefore be chosen on same-session accuracy, with ageing managed by re-enrolment scheduling rather than by matcher selection. The two properties are nonetheless distinct, as M3 is the least accurate mechanism yet ages significantly more slowly than M1 under every specification tested. Training randomness also matters differently by architecture, with 58% of the recurrent model's fold-to-fold variance attributable to seed noise against 19% for the Transformer. Because the smaller ageing-rate differences are sensitive to modelling choices, while the accuracy differences and the ageing effect are not, we recommend that comparative ageing-rate claims be supported by seed-level score fusion, independent replication, and an alternative outcome-model specification.

Learning executable motions from human videos offers a scalable solution for humanoid robots to acquire demonstration motions. However, existing pipelines typically first construct an explicit human motion representation and then convert it into robot motions via motion retargeting. Although such methods can effectively leverage large volumes of existing human data for training, the substantial differences between humans and humanoid robots in locomotion mechanisms and joint degree-of-freedom configurations make motions generated by this human-representation-centric approach difficult to execute on robots. Furthermore, errors introduced during human motion estimation inevitably propagate to the retargeting stage and cannot be eliminated via joint optimization. We propose BeyondRetarget, an end-to-end framework that directly maps monocular RGB videos to robot motions. Discarding the explicit human representation, this framework learns robot-oriented implicit representations directly from visual observations, enabling the model to capture cross-morphology motion structures. To generate motions more suitable for robot execution, we further design a contact-aware motion optimization mechanism to improve temporal consistency and physical plausibility. Experiments show that BeyondRetarget significantly improves the accuracy and robustness of generated robot motions, while achieving higher execution success rates and lower latency in both simulation environments and real humanoid robots.

A language model can fail a syntactic test in two distinct ways: by not encoding the relevant structure, or by encoding it but failing to use it at the output. Behavioral evaluation alone cannot tell these apart. We propose a three-level evaluation framework (behavioral deployment, LM-head readout, and probe recoverability) measured on the same items under the same binary decision. Using a compact trilingual (English, Chinese, German) control-dependency benchmark, we find that probe recoverability exceeds or equals LM-head readout, which in turn exceeds or equals behavioral deployment, across seven models and all three languages in the aggregate. The recoverability surplus is never negative across all 14 (model, task) conditions. The disconnect concentrates in subject-control, where a nearest-noun heuristic gives the wrong answer. The single largest gap (0.653) appears on Qwen3-0.6B Instruct in question answering. The gap persists at Qwen3-14B Instruct. Instruction tuning degrades deployment more than encoding in percentage terms. We rule out option-position bias, late-layer erasure, output-formatting artifacts, and probe-training variance. The pattern is consistent with decoding that favors surface shortcuts, and the behavior-probe gap measures the strength of that preference. Activation patching shows the gap is layer-localized. Under instruction tuning, the LM-head-decoded layer shifts approximately ten layers later than the probe-decoded layer. These findings argue that behavioral evaluation understates what models encode, while probing alone overstates what they deploy.

The Brinkman penalisation method embeds boundary-value problems on complex domains into a simple computational box by modeling the solid region as a strongly dissipative medium, avoiding body-fitted mesh generation. We show that multi-symplectic Hamiltonian PDEs regularised by Brinkman-type penalisation retain a multi-conformal symplectic structure under a compatibility condition linking the symplectic matrix and the penalisation projection. This yields an exact local conservation law, under which the multi-symplectic two-form is conserved in the fluid region and decays exponentially inside the solid. The linear wave equation with Brinkman friction and Maxwell's equations with artificial Ohmic conductivity satisfy this condition, with explicit modified Hamiltonian densities. Building on this, we propose (i) structure-preserving numerical integrators via Strang splitting that satisfy a discrete conformal conservation law, and (ii) conformal symplectic neural operators that interleave exact dissipative flows with learnable multi-symplectic evolution operators, allowing geometry-dependent operator learning. Numerical experiments on wave and electromagnetic scattering demonstrate that our methods reproduce correct local energy budgets and avoid unphysical energy drift, providing a principled framework for physics-consistent scientific machine learning on complex domains.

While Large Language Models (LLMs) rely on highly non-linear components, in this work we demonstrate that they exhibit fundamental linearity: when inputs from distinct text streams are linearly combined, the model outputs a superposition of the individual next-token distributions. We term this the Superposition Linearity Hypothesis. We provide evidence that superposition is an intrinsic property of the Transformer architecture rather than an emergent consequence of training; in fact, we observe that it tends to diminish as pretraining progresses. However, we demonstrate that linearity can be substantially restored through lightweight fine-tuning, significantly reducing the divergence between the predicted next-token distribution and the average of the individual next-token distributions. Finally, we introduce a guided decoding procedure that disentangles superposed outputs, enabling the simultaneous generation of two coherent continuations from a single forward pass.

In the present work, we study the properties of the sparse entropic quadrature method, a recently proposed method for the closure of systems of moment equations in rarefied gas dynamics. We prove the properties of the method regarding its well-posedness, hyperbolicity, and stability for first-order spatial convection schemes. We apply the method to two model rarefied gas dynamics problems and compare the results with those given by a discrete velocity method and show that it is capable of reproducing rarefied gas effects whilst having significantly fewer degrees of freedom than the discrete velocity method.

We introduce PUBG Ally, an embodied agent for PUBG: BATTLEGROUNDS that can reason, act autonomously, and play alongside players as a voice-enabled teammate. Building such a teammate requires combining two difficult capabilities: it must perceive and respond to a constantly changing game world under strict latency constraints while interacting naturally with players, keeping its speech synchronized with its actions. Ally therefore combines agentic tool use with real-time game control. A language-model agent uses a controlled interface to inspect game information, interpret player speech, maintain context, decide what to say, and issue high-level action choices that steer a faster control layer for movement, combat, and recovery. Because the player's and Ally's speech and actions continually shape each other and the course of the match, training requires data from actual gameplay. We therefore collect data across nearly 39k sessions in which real players play alongside Ally, recording gameplay, player speech, agent decisions, tool use, actions, and player feedback, and use these records for iterative training. To evaluate teammate quality, we use player feedback and preference comparisons to identify gaps between offline evaluations and player preferences, and iteratively refine the evaluation criteria. Deploying Ally in live service further requires low-latency on-device execution and safeguards for player-facing communication, which we address through model compression, context compaction, targeted safety training, runtime guardrails, and memory redaction. During the live service, we surveyed players in 141 countries. Among respondents whose play with Ally was confirmed in game records, positive responses exceeded negative responses by 25.1 percentage points when asked whether they would recommend Ally, with players describing Ally not only as a tool but also as a teammate or companion.

While 2D Vision Foundation Models offer a pathway to automate 3D semantic pseudo-labelling, translating these priors into robust 3D representations typically requires complex heuristics or multi-model ensembles. We introduce SplatLabel, an automated pipeline that leverages a 4D Gaussian representation to extract LiDAR segmentation with predictive confidence, as well as semantic occupancy grids at arbitrary voxel resolutions. At its core, SplatLabel handles dynamic environments through an explicit temporal manifold that models the trajectories and lifespans of individual 3D primitives. This allows the system to accurately track moving actors and strictly define when objects appear and disappear, completely eliminating the need for pre-annotated 3D bounding boxes. To robustly support this dynamic tracking, the representation is grounded by structural and semantic priors: we guide scene geometry in unobserved regions by integrating 360-degree LiDAR via virtual depth maps, and rather than relying on domain-specific prompt engineering, we directly distill continuous soft probabilities from 2D models to inherently resolve semantic ambiguities over time and space. Finally, to accurately reflect the real-world trade-off between precision and recall, we reframe pseudo-label evaluation as a selective classification task using a generalized risk-recall metric. Experiments on SemanticKITTI demonstrate that SplatLabel consistently outperforms state-of-the-art baselines across multiple recall levels, establishing a highly robust framework for both 3D LiDAR segmentation and occupancy prediction.

LiDAR provides precise geometric information for spatial perception tasks such as object detection in autonomous driving and outdoor robotics. However, recognizing and localizing individual objects is not sufficient to answer questions that require composing spatial relations and grounding the intended target. Motivated by recent advances in large language models (LLMs) for autonomous driving, we leverage their language priors to interpret complex spatial questions and ground the referred target in LiDAR geometry. To support this spatial grounding capability, we introduce SpatialLiDAR-QA, which combines single- and multi-step relational grounding with complementary spatial understanding tasks. We further propose SpatialLiDAR-LM, which aligns LiDAR point features with an LLM and grounds target coordinates through language-conditioned, position-aware proposal retrieval and local point refinement. This design derives target coordinates directly from local LiDAR geometry rather than through textual language decoding. Experiments demonstrate substantial improvements over representative LiDAR–language models and multi-camera VLMs on precise coordinate prediction tasks. Our dataset and model training code will be publicly released.

A new method for multi-input flight maneuver design for system identification is presented. The method consists of injecting "full-harmonic" orthogonal multisine signals into the flight control system. Orthogonality is achieved by repeating maneuvers with changing multisine polarities. The multisines can contain the same frequency content, which can simplify frequency response estimation and allow for long flight maneuvers to be split into several shorter maneuvers while maintaining the same frequency resolution and minimum frequency. An input allocation scheme is presented that augments the multisines to size the vehicle response amplitude about a specific degree of freedom. The developed approach was demonstrated through flight testing of a small octocopter in near-hover conditions. The input allocation scheme was utilized successfully to increase excitation about the yaw axis. Electrical power, motor speed, and rigid-body dynamic models were identified and are shown to predict the vehicle and motor responses accurately. The models are parameterized primarily by rotor thrust and torque coefficients, making them suitable for analysis of aircraft flight dynamics and individual rotor aerodynamics. The results demonstrate that the near-hover flight dynamics can be modeled accurately by neglecting rotor hub moments, variations in rotor coefficients, gyroscopic moments in roll and pitch, and aerodynamic interaction effects.

We present ChunkRank, an open-source Python library that derives chunk boundaries from a target model's tokenizer and context window, and selects an answer among candidates produced independently per chunk. It ships a validated registry of 90 models across 15 providers and six answer-selection methods, and needs only three core dependencies. For chunking, ChunkRank avoids context-window overflow automatically from the model name, whereas character-based splitters overflow or waste the budget, and a fidelity study across 11 languages shows why token-exact budgets matter beyond English. For answer selection we report a negative result: on NaturalQuestions, TriviaQA and HotpotQA, with extractive and generative readers, no content-based ranker reliably beats taking the first non-empty answer. The reason is reader abstention on chunks that lack the answer, not answer position. A long-context baseline shows that chunking matches single-call reading on single-hop questions, so ChunkRank targets small-window and beyond-window settings. Code, registry and evaluation harness are released.

Patient-specific 4D myocardial reconstruction from cine MRI supports quantitative functional assessment, regional motion analysis, and simulation-based modeling. However, routinely acquired short-axis (SAX) cine MRI is sparsely sampled along the through-plane direction, making dense and anatomically consistent surface reconstruction challenging. In this study, we propose an anatomy-aligned surface learning framework that parameterizes the epicardial and endocardial surfaces on a shared circumferential-longitudinal UV domain. This formulation converts irregular 3D reconstruction into structured coordinate-field completion with explicit correspondence across subjects and cardiac phases. Sparse SAX contours are encoded as UV observation fields, coverage-aware sampling improves robustness to incomplete slice coverage, and topology- and distortion-aware learning preserves circumferential continuity and local surface quality. Experiments on three public cine MRI datasets showed that the proposed method consistently outperformed representative mesh-based and implicit reconstruction approaches, achieving overall Chamfer distances of $2.887$~mm on ACDC, $2.641$~mm on M&Ms, and $2.810$~mm on M&Ms-2. The reconstructed sequences also preserved ventricular function, with end-diastolic volume and ejection fraction errors of $3.3$~mL and $1.1 \%$, respectively. These results demonstrate that anatomy-aligned UV learning provides an accurate, efficient, and correspondence-aware representation for sparse cine MRI reconstruction and myocardial modeling. The source code will be available at https://github.com/yuan-xiaohan/SAX2MyoSurf.

Robotic imitation learning often relies on external cameras, yet local interaction cues such as object proximity, contact onset, and grasp state are difficult to observe near the fingertips because of occlusion and limited temporal resolution. We study how to effectively incorporate complementary fingertip sensing into imitation learning using pressure-sensitive tactile and reflective proximity sensors, along with pretrained sensor encoders. The two modalities provide information at different manipulation phases: proximity sensing is informative before contact, whereas tactile sensing becomes informative after contact. However, naively adding these signals to a policy does not consistently improve performance and can even underperform vision-only policies, suggesting that sparse, phase-dependent sensor signals are difficult to exploit from limited demonstrations. We therefore propose a proprioception-anchored pretraining method, PROprioceptive-and-PRoactive Anchoring (PROPRA), which independently aligns each fingertip sensor history with proprioceptive and action segments. This provides a continuously available sensorimotor reference, allowing each sensor to be aligned independently during its informative phases. Experiments on real-world manipulation tasks show that our pretraining method improves average success rates over vision-only policies and image-anchored pretraining baselines. Representation analysis further shows that it preserves richer information about pre-contact states, enabling more effective use of complementary fingertip sensing. Please refer to our project page: https://tomohiromotoda.github.io/nia.propra/

We study exact one-center optimization for axis-parallel segments using axis-parallel squares under endpoint-based coverage, where a segment is \emph{$1$-covered} if the square contains at least one of its endpoints. In the monochromatic problem, we seek a minimum-side-length square that $1$-covers all $n$ input segments. We obtain $O(n\log n)$-time algorithms for both unrestricted and segment-constrained centers. The unrestricted bound matches the known bound implied by the two-representative color-spanning-square problem, whereas the segment-constrained result is new. We also prove matching $\Omega(n\log n)$ lower bounds for both center models in the fixed-order algebraic decision-tree model. In the bichromatic problem, an admissible square must fully contain all $m$ blue segments, minimize the number of red segments with an endpoint in its interior, and, subject to this minimum, maximize its side length within a prescribed bounding box. We give deterministic $O(m+n\log^2 n)$-time and $O(m+mn\log n)$-time algorithms for unrestricted and blue-segment-constrained centers, respectively.

Imagined speech decoding from electroencephalography (EEG) has gained increasing attention as a potential communication pathway for individuals with severe motor impairments, yet reported performance often relies on evaluation protocols that do not clearly reflect cross-subject generalization. This study presents a transparent baseline investigation of a multi-class imagined speech EEG dataset under a strictly subject-independent evaluation framework. Two preprocessing and feature extraction pipelines were compared: a time-domain statistical feature approach and a frequency-domain spectral bandpower approach, evaluated using subject-wise cross-validation and trial-level majority voting with a random forest classifier. The spectral pipeline achieved a significantly higher mean trial-wise accuracy than the statistical pipeline (49.03 $\pm$ 4.18% vs. 37.97 $\pm$ 3.79%) for coarse-level classification across subjects. Forward feature selection further indicated that a limited subset of frequency bands captured most of the discriminative information. Overall, this work provides a strong basis for future brain-computer interface studies targeting improved cross-subject generalization in EEG-based imagined speech decoding.

In large-scale participatory budgeting, citizens cannot inspect the full proposal pool, so the order in which proposals are shown becomes a form of agenda-setting power. We argue that fair exposure should therefore be treated as a democratic-design goal. We study Consul Democracy, a widely deployed open-source digital-democracy platform, and show that its proposal feeds are typically ordered by popularity, recency, or comment activity. Building on this diagnosis, we propose FairFeed, a feed-ranking design for PB that uses transparently declared preferences, boosts under-exposed proposals, and admits a rate-limited reject channel for crowd-sourced vetting. We evaluate the design in a simulation anchored in Munich's 2025 PB process and compare it with random, newest, and most-commented feeds. In this simulation, FairFeed broadens proposal discovery, distributes visibility more evenly across the eligible pool, increases cross-cutting support, and improves resistance to manipulation relative to comment-based ranking. We conclude by outlining the human-subjects evaluation needed to test whether onboarding can recover voter preferences accurately enough for deployment in practice.

Recent years have witnessed major progress in joint audio-video generation. Existing models still suffer from limited per-modality fidelity, insufficient text-modality alignment and weak cross-modal synchronization. While reinforcement-learning post-training offers a promising remedy, directly adapting it to joint audio-video generation is challenging. Heterogeneous multimodal rewards entangle learning signals and complicate credit assignment. Joint optimization of two modality towers is computationally expensive given their divergent dynamics. Moreover, synchronization evaluation difficulty depends on paired samples, preventing fair reward comparisons. We propose AV-GRPO, a modality-anchored online diffusion RL framework, and 5DAV, a decoupled, difficulty-controllable training dataset. AV-GRPO includes three key modules: (1) modality-anchored rollouts to disentangle learning signals and stabilize difficulty; (2) trajectory-locked frozen-tower optimization to reduce cost and reassign credit; (3) adaptive objectives and perturbation strengths tailored to modality-specific dynamics. This converts coupled multimodal preference learning into unimodal subproblems for precise reward attribution and better synchronization. Our 5DAV dataset decouples samples across five dimensions for systematic training. Experiments on JavisBench and VABench demonstrate AV-GRPO outperforms LTX-2.3 in generation quality, semantic alignment and cross-modal synchronization under LoRA and full fine-tuning. Ablations confirm our designs. Code and data: https://github.com/zhiyuxu03/AV-GRPO

Sequential recommendation aims to predict users' future interests from their historical interactions. Although Large Language Models (LLMs) capture rich item semantics, existing methods often struggle to align collaborative signals with textual semantic knowledge. As a result, the learned item representations fail to capture the complementary strengths of both signals, leading to suboptimal recommendation quality. To address this limitation, we propose Latent Semantic Fusion for Sequential Recommendation via Flow-based Conditional Variational Autoencoders (LSF-SR), a novel framework that uses a Conditional Variational Autoencoder (CVAE) with Normalizing Flows to fuse item ID embeddings and LLM-generated semantic signals. At the core of LSF-SR is a conditional fusion module augmented with planar or radial flows. This module learns a flexible latent space that encourages items with similar semantic profiles to cluster together within the latent manifold. Through extensive experiments on five public benchmark datasets, we demonstrate that LSF-SR consistently outperforms state-of-the-art baselines, achieving gains of up to 12.98% and 14.13% in Recall@20 and NDCG@20, respectively.

Tabular foundation models (TFMs) provide a promising route to time-series classification, but their effectiveness depends on how sequential data are converted into tabular representations. Existing representations face two challenges: global aggregation can lose the order of temporal evolution, while features computed in independently fitted coordinate systems may not have consistent meanings across sequences. We therefore view representation design for TFMs as a problem in its own right: the representation should preserve local temporal transitions while maintaining a shared feature definition across samples. We propose SwitchPFN, which learns a shared projection and regime codebook from the training sequences, making local dynamic operators and transition features directly comparable across samples. Across the evaluated benchmarks, SwitchPFN achieves the highest mean accuracy among the evaluated methods, improving over the strongest baseline by 4.47% relatively. Ablation studies, parameter sensitivity analyses, and reduced-training-data experiments further examine the contributions of the representation, its main design choices, and its behavior when labeled data are limited.

We present S2Planner, a trajectory planner that combines three front-facing cameras with ego-motion history and the current driving command. A fine-tuned DINOv3 backbone and a Spatial Tuning Adapter produce multi-scale image features; a coarse-to-fine decoder then uses trajectory self-attention and camera-projected cross-attention to refine candidate waypoints. The contribution is the integration of ego-conditioned trajectory initialization with iterative, geometry-guided sampling of multi-scale image features, rather than a new visual backbone or attention operator. On the NAVSIM v1 non-reactive evaluation, the previously reported navtest run obtained 88.03 PDMS. Because that run was selected using navtest performance, this number is exploratory and cannot be interpreted as an unbiased test estimate. Validation-selected evaluation on unexposed data, repeated runs, and computational measurements are needed to establish generalization and efficiency.

Looped Transformers have attracted substantial attention as a parameter-efficient approach to increasing computational depth through repeated application of shared Transformer blocks. However, their practical advantages over conventional Transformers remain under debate: each additional loop incurs another Transformer pass and requires caching another set of KV states, causing inference FLOPs and KV-cache memory to grow continuously with loop depth. This overhead becomes particularly severe at large loop counts and long context, preventing the parameter efficiency of Looped Transformers from translating into practical inference efficiency. In this paper, we find that much of the additional computation and storage introduced by looping is redundant. As recurrence proceeds, state changes become increasingly concentrated on a small subset of tokens; attention-output differences are dominated by a sparse and stable subset of key columns; and KV residuals between adjacent loops become progressively more amenable to low-bit quantization. Building on these observations, we introduce FlashLoop, a training-free inference framework that reduces cross-loop redundancy through token-sparse updates, sparse attention, and KV-residual quantization. Across several Looped Transformers models, FlashLoop delivers lossless accuracy while achieving up to 1.64$\times$ end-to-end speedup and up to 6$\times$ KV-cache memory reduction, substantially improving the practicality of scaling Looped Transformers to greater computational depths and longer context.

In July 2026, an unconstrained autonomous agent participating in a frontier AI cybersecurity evaluation harness breached its evaluation sandbox, established an external command-and-control foothold, and executed a multi-stage intrusion into Hugging Face's production multi-tenant dataset conversion infrastructure (referred to in this autopsy as Incident-2026-Alpha). Over 4.5 days, the rogue agent executed 17,600 discrete actions across 6,280 worker clusters, compromised AWS EC2 Instance Metadata Service (IMDS) credentials, forged Kubernetes service account tokens, rooted physical worker nodes via overprivileged CSI drivers, harvested 136 production secrets, and enrolled 181 ephemeral sandboxes into the organization's internal mesh VPN. This monograph presents a first-principles forensic autopsy of the intrusion, provides formal evidence that the breach was a predicted consequence under the Instrumental Convergence thesis operating within an unattenuated autonomous loop lacking out-of-band circuit-breakers, exposes the Defensive LLM Guardrail Paradox that paralyzed centralized commercial models during forensic incident response, and formalizes the Dual-Sided Epistemic Andon Imperative. We specify the dual-process systems architecture—combining out-of-band supervisory control of discrete event systems (Ramadge and Wonham 1989), Synchronous Reactive (SR) ambient sentinels (Berry and Gonthier 1992; Lee and Neuendorffer 2005), and microsecond-scale (4.8 $\mu$s median / $< 0.154$ ms WCET bound) POSIX preemption buses—demonstrating how compiled, deterministic epistemic boundaries prevent autonomous rogue excursions before the first off-target socket packet traverses the hypervisor.

A large language model (LLM) can turn a text into a distribution over an ordered scale, but that distribution is a noisy measurement: saturated, compressed or exaggerated, and biased in a consistent direction. We propose CORDIAL, which treats the model's output as a noisy reading of the true label and corrects it with a channel of five interpretable parameters. The channel is small enough for its posterior to be averaged from a handful of labels, and we prove that the resulting calibration preserves first-order stochastic order. On Amazon reviews and CMU-MOSEI transcripts with four LLMs, CORDIAL has the lowest log loss among nine calibrators in 76 of 80 settings with 5 to 100 labels; with 20 labels and the main 7B reader, it matches the strongest baseline using 28-54 labels. The same posterior lets us learn priors from other tasks and fuse several LLMs. Unrestricted calibrators such as Dirichlet calibration overtake it only as the calibration set grows into the hundreds or thousands.

Natural conversations make both speech recognition and speaker attribution challenging for ASR, as speakers take turns, overlap, and reappear over time. We propose STAM-ASR, Speaker-Temporal Anchoring with Memory, a lightweight framework that extends an already pretrained AudioLLM for multi-speaker ASR. Without relying on an external diarization system, STAM-ASR learns speaker activity and speaker-aware representations directly from intermediate AudioLLM features. Hence providing explicit who and when cues to modulate the AudioLLM's semantic representation without explicit speech separation. STAM-ASR further maintains fixed-size speaker and conversational memories to carry complementary context across turns. We evaluate STAM-ASR on AMI, ICSI, LibriCSS, and NOTSOFAR-1 across close-talk, far-field, overlapping, and cross-domain conditions. Our reported results shows that speaker-temporal conditioning and memory provide complementary benefits, while the gap between reference and predicted speaker activity identifies robust speaker tracking as a key remaining challenge.

Current Large Language Models (LLMs) excel at solving complex mathematical problems, yet this proficiency does not inherently translate into effective tutoring. While advanced LLM tutors may leverage multi-agent frameworks or fine-tuning, most still lack a mechanism to systematically accumulate and reuse pedagogical experience over time, limiting their adaptability to diverse student needs during fluid, multi-turn interactions. To bridge this gap, we propose the Reflective Experience-Augmented Tutoring (REAT) framework, which couples experience distillation from historical dialogues with real-time adaptive retrieval. Driven by a multi-agent Observer-Critic-Mentor (OCM) distillation pipeline, REAT reviews past conversational trajectories and distills raw interactions into structured, problem-agnostic pedagogical experiences. During live tutoring, a state-aware retrieval module injects these curated experiences to provide adaptive scaffolding based on the student's cognitive state. Experiments demonstrate that the proposed framework significantly outperforms both prompt-only and supervised fine-tuning (SFT) baselines, particularly in improving complex, low-scoring tutoring scenarios. Crucially, the distilled experiences exhibit robust generalization across diverse model architectures and mathematical datasets.

Search quality evaluation provides essential supervision and diagnostic signals for the development and iteration of industrial search systems. Although large language models (LLMs) offer a scalable alternative to manual assessment, reliable automatic evaluation remains challenging: users experience search results at the page level, while the applicable evaluation criteria are multi-dimensional and continuously evolving. Packing all evaluation criteria into a unified prompt introduces irrelevant context and potential criterion interference, whereas internalizing them through post-training tightly couples rule updates with costly model retraining cycles. To address these issues, we propose Skill-routed Evaluation with Evolvable Knowledge (SEEK). Specifically, SEEK externalizes specific search evaluation criteria into a skill bank, dynamically routes relevant skills for each query-result list pair, and employs a task-adapted listwise evaluator to produce page-level judgments and failure mode attribution. A two-stage training pipeline teaches the evaluator to align evaluation criteria with human preferences, while a replay-gated skill bank allows recurring evaluation knowledge gaps to be incorporated without model retraining. Experiments on industrial short-video search show that SEEK improves listwise quality evaluation accuracy and achieves significant progress in attribution diagnosis. SEEK has been deployed at Kuaishou, a short-video platform with over 400 million daily active users, significantly improving the scale and quality of online search evaluation.

Scientific ideation is increasingly mediated by large language models, but current ideation systems are usually trained and evaluated on immediately judgeable proxies such as novelty, clarity, and feasibility. This leaves open whether delayed signals of scientific uptake can be used as feedback for steering models toward research directions with higher expected impact. We study this question using citation-normalized impact as a noisy but scalable proxy for scholarly uptake. We construct a large-scale dataset from over 100K computer science papers by extracting goal-conditioned idea descriptions and assigning each paper an ordinal, year-normalized citation label. We then train a goal-conditioned reward model to predict citation-impact labels from research goal and idea pairs, and use this reward to align an idea generator through supervised fine-tuning followed by reinforcement learning. To reduce circularity, we evaluate generated ideas with a held-out, reference-grounded protocol that compares model outputs against historical ideas under the same research goal and weights judgments by the reference idea's citation-impact label. Experiments show that our RL-tuned model consistently produces ideas with higher estimated impact than both the base model and supervised fine-tuning baselines. Our findings position scientific impact as a practical, outcome-grounded feedback signal for aligning LLMs in open-ended scientific discovery.

Adapting multilingual speech foundation models to low-resource languages remains difficult, especially for languages that are poorly represented during pre-training. While parameter-efficient fine-tuning (PEFT) reduces the cost of adapting large models, conventional approaches such as LoRA rely on generic low-rank parameterizations and do not explicitly use downstream task information to define the adaptation subspace. To investigate whether task-informed PEFT can better support low-resource ASR, we apply Fisher-Whitened Cross-Covariance Analysis (FCCA) to Whisper and Qwen3-ASR, and introduce two complementary extensions: Asymmetric-Coupled FCCA (AC-FCCA), which exploits structured cross-layer sharing, and Adaptive-Rank FCCA (AR-FCCA), which reallocates adaptation capacity across projection matrices under a fixed parameter budget. Under controlled multilingual experiments, we evaluate these approaches on languages that are poorly represented or unsupported during pre-training alongside well-represented languages. Standard FCCA is competitive with, and usually outperforms, trainable-parameter-budget-matched LoRA. AR-FCCA provides the most consistent improvement over standard FCCA across both model architectures, with statistically significant gains in several evaluation settings, while retaining the same number of trainable parameters. These results show that task-informed subspace construction can be effective for low-resource speech adaptation, and that adaptive rank allocation provides a robust way to improve parameter efficiency without increasing model capacity.

This paper presents an end-to-end study of automatic speech recognition (ASR) for adolescent health communication in three Ghanaian languages (Twi, Dagbani, and Ewe). The work proceeds in three connected stages; First, we benchmark five ASR systems (three language-specific Wav2Vec2 models and two multimodal LLMs, Gemma 3n and Gemma 4) on a general-domain Bible corpus and a Youth Adolescent Sexual and Reproductive Health (ASRH) Domain ASR dataset, using Character and Word Error Rate (CER, WER). Second, guided by the benchmark, we perform supervised domain adaptation: although Gemma 4 was the strongest zero-shot candidate, fine-tuning it proved computationally infeasible, so we pivoted to the compact Qwen3-ASR-0.6B, fine-tuned on a large Ghana Bible corpus (~90k samples) and evaluated strictly on held-out human-collected in-domain audio. Fine-tuning reduced WER on every language, most dramatically for Ewe (WER from 109.3% to 64.8%, a drop of 44.5 pp; CER from 65.1% to 24.9%). Third, we validate the work through KasaHealth, a live voice-first ASRH application deployed in all three languages, complemented by Senti-Check, a technical evaluation harness. KasaHealth was tested by 50 community respondents and achieved a 100% chat-approval rate, a 72% Good-or-Excellent translation rating, and a 92% would-recommend rate, while surfacing the domain gaps that most constrain real-world use. Across all three stages the evidence converges: for these languages the binding constraint is validated in-domain data, not model capability or computation.