Learning Using Privileged Information

Follow this topic Ask about this topic

Momentum

10 papers in the last four weeks, up 100% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 50

Oct 6, 2026cs.RO

Seeing Through the Displaced Frame: Privileged Noise Distillation for Vision-Force Precision Assembly

Pose error in precision assembly can corrupt not only what a robot observes but also the coordinate frame in which it acts. On the FORGE benchmark, the official state-based policy succeeds in 97% to 99% of episodes with the true pose but only 32% to 60% at the benchmark's

σ=5

mm pose-noise setting. The same estimated pose enters the observation and anchors the action frame, making the offset unidentifiable from proprioceptive state alone before contact. We supply this missing information during training in two ways. A privileged teacher observes the offset in simulation, while clean demonstrations can instead be relabelled into the displaced frame in closed form. The deployed student is trained with behaviour cloning followed by one DAgger round and receives only noisy state, a raw wrench window, and two RGB cameras at test time. On the unmodified FORGE tasks, the teacher-route student maintains 92% to 99% success across

σ=0

to 5 mm, while six non-privileged baselines fall to 2% to 80%. A matched behaviour-cloning experiment isolates the source of this robustness. With the same student architecture, data budget, and training procedure, demonstrations generated without offset access yield only 31.5% success at

σ=5

mm, whereas privileged and relabelled demonstrations reach 88.7% and 95.8%. Deployed zero-shot on a Franka, the student reaches 83.3% pooled success at

σ=5

mm against 34.4% for the strongest state-based policy. Deployable sensing alone is insufficient. Robustness requires supervision that encodes compensation for the latent frame offset.Project page: https://drychang.github.io/displaced-frame/

Ching-Hsiang Chang, Tzu-Yu Chuang, Yi-Hsiu Lee +3

National Tsing Hua University, Hsinchu, Taiwan. · National Yang Ming Chiao Tung University, Hsinchu, Taiwan.

Robotic Manipulation Force-Controlled Robotic Manipulation Robot Imitation Learning Learning Using Privileged Information Robotic Assembly

Sep 30, 2026cs.LG

ReSAIL: Mitigating Collapse in Iterative Agent Self-Distillation

Iterative self-distillation enables LLM agents to learn from successive deployments, offering a path toward recursive self-improvement (RSI). Yet our experiments with existing methods reveal a collapse in deployment performance across cycles, while task performance with privileged information (PI) also declines. We address this collapse by prioritizing informative interaction steps for distillation and preserving PI-conditioned behavior as the student becomes the next teacher. We introduce Retentive and Selective Augmentation for Iterative Self-Distillation (ReSAIL), a plug-in augmentation for iterative PI-based self-distillation. ReSAIL selects interaction steps where PI most strongly changes the teacher's predictions and balances the resulting distillation losses across trajectories. It also regularizes the student's PI-conditioned output distributions toward those of the frozen teacher at selected and unselected steps to preserve PI-conditioned behavior for supervision in the next cycle. On ALFWorld and TextCraft, ReSAIL sustains substantial gains across model scales over three cycles, with an average absolute gain of 22.5% in final-cycle success rates when added to self-distillation baselines. Sensitivity-guided selection of offline data also improves action prediction accuracy for multimodal GUI agents on AITZ. These findings provide the first evidence that a more robust learning mechanism can effectively mitigate performance collapse in iterative agent self-distillation over deployment trajectories.

Shengjie Jin, Hengbo Xu, Zelong Sun +2

Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China

On-Policy Self-Distillation LLM Agent Self-Improvement Self-Distillation Learning Using Privileged Information

Sep 30, 2026cs.SD

RAST: Resolution-Aware Privileged Structure Transfer for Low-Resolution Audio Activity Recognition

Audio is increasingly used for human activity recognition (HAR) because it captures object interactions, environmental events, and contextual cues in everyday environments. High-resolution (HR) audio provides rich acoustic information for model development but incurs substantial energy and storage costs and may expose sensitive speech content. Low-resolution (LR) audio offers a more privacy-preserving and resource-efficient alternative for deployment, but reduced sampling rates can remove acoustic cues essential for activity recognition, leading to significant performance degradation. We formulate this training-deployment mismatch as sensor-resolution privileged learning, in which HR audio is available during training, while inference relies exclusively on LR audio. We propose RAST, a resolution-aware transfer framework that compresses HR teacher representations by preserving token-level information and neighborhood structure before performing localized HR-LR alignment. Experiments on the SAMoSA and AudioIMU datasets show that RAST consistently outperforms LR-only training and direct teacher-transfer baselines, improving LR-only recognition by up to approximately 7.8% while requiring only LR audio at inference.

Ji Hwan Park, Gautham Krishna Gudur, Yufei Shen +2

The University of Texas at Austin Austin, Texas, USA

Audio Representation Learning Human Activity Recognition Learning Using Privileged Information Knowledge Distillation

Sep 26, 2026cs.AI

Instruct, Not Answer: Using Instruction Privileges in On-Policy Context Distillation

On-Policy Context Distillation (OPCD) has recently emerged as a powerful technique for transferring context to student models and for self-improvement. In OPCD, the teacher is conditioned on privileged information, and the goal is to minimize the Kullback-Leibler (KL) divergence between the privileged teacher and the student, evaluated on student-generated tokens. Many existing studies show that using instance-specific gold answers or gold demonstrations as the default privilege can hurt training performance, especially out-of-distribution (OOD). In this work, we instead design general instructions that target common student mistakes observed on the training samples, and show that such simple instructions can outperform gold as the OPCD privilege. In autoformalization tasks, using a matched formatting instruction as the privilege could outperform gold in OOD accuracy by a large margin. In 7 out of 8 experiments using ProverQA, ProofWriter, and ProntoQA as datasets, and Qwen3-Thinking and Olmo3-Thinking families as models, matched instruction privileges outperform gold in OOD by 4 to 17 points, while remaining on par with gold in-domain. Each instruction is only a few sentences (and thus contains much less information compared to all instance-specific gold) and is applied uniformly to every training sample. These results indicate that a general instruction, which applies equally to source and target domain examples, can be substantially more transferable than instance-specific gold in OPCD while maintaining in-domain performance.

Hantao Yu, Xiaoxue Han, Udaya Ghai +4

Columbia University · Amazon Web Services

OOD Generalization On-Policy Distillation Context Distillation Learning Using Privileged Information

Sep 24, 2026cs.AI

From Self-Distillation to Self-Practice: Privileged Information for Multi-Turn Agents

On-policy self-distillation (OPSD) has become a popular recipe for post-training LLM agents. It supervises the agent model at the token level with a stronger teacher view of the same model, obtained by conditioning on privileged information (PI). In this work, we show that in multi-turn agents, this paradigm teaches the student to act with confidence but without the information behind it. The trained agent behaves as if it had privileged information it never observed, and its performance falls well short of plain RL, in the worst case below the untrained base model. Therefore, we propose Privileged Self-Practice (PSP), which keeps the PI and moves it from the loss to the sampler. When the student's rollouts on a task mostly fail, we inject a short per-task instruction written by an analyzer model, sample the task again with the instruction in context, and train on the result with an unchanged GRPO objective. The privileged information stays in the prompt and never enters the loss. Across AppWorld and SWE-bench Verified, with three different student models, PSP obtains the best average score in every setting and is the only method that consistently outperforms plain GRPO, improving task-goal completion by up to 65% on AppWorld and the resolved rate by up to 61% on SWE-bench Verified.

Xingyu Su, Abhishek Kumar, Qing Ping +5

Texas A&M University · AWS AI, Amazon

On-Policy Self-Distillation LLM Agent Training Learning Using Privileged Information RL for LLM Agents

Sep 22, 2026cs.RO

PLAT: Sparse Timed Keyframe Motion Tracking for Humanoid Control via Privileged Latent Transition Learning

Humanoid motion tracking policies rely on dense frame-by-frame references, limiting their use as high-level motion controllers for planning and interactive motion generation. We study \emph{Sparse Timed Keyframe Motion Tracking}, where a policy receives only sparse future keyframes and their desired arrival times, and must execute stable whole-body motions that reach successive goals. We propose \textbf{PLAT}, a three-stage sparse timed keyframe motion tracking policy learning framework with \textbf{P}rivileged \textbf{LA}tent \textbf{T}ransition learning. PLAT bridges dense motion tracking and sparse goal-conditioned control by exploiting dense goal sequences as privileged supervision during training while requiring only sparse timed keyframe commands at deployment. A pretrained dense tracking expert first provides robust motion priors. A privileged latent prior is then learned through DAgger-style imitation, followed by latent residual reinforcement learning that refines latent transitions instead of directly optimizing actions. Extensive simulation experiments demonstrate that PLAT maintains accurate and stable sparse timed keyframe tracking across varying planning horizons, with particularly strong performance under long-horizon commands. Successful deployment on a Unitree G1 humanoid robot further demonstrates the effectiveness and practicality of PLAT for sparse humanoid motion control.

Zepeng Wang, Jiangxing Wang, Chao Ma +2

Wuhan University. · BeingBeyond. · Peking University.

Robot Imitation Learning Humanoid Motion Tracking Learning Using Privileged Information

Sep 22, 2026cs.LG

What Should a Self-Teacher See? Privileged Context Design for On-Policy Self-Distillation

More privileged information does not always make a better teacher. We study this tension in on-policy self-distillation (OPSD), where a frozen copy of the base model scores the student's own rollouts under privileged context, conventionally a complete reference solution that bundles the final answer with one particular reasoning path. Holding the student view and training fixed within each scale, we compare that default against three abstractions compiled offline, a named strategy, a method-independent framing, and a problem category, and against an answer-only control that keeps the destination but removes the path. In the primary runs on competition mathematics, the best intermediate contexts improve the in-domain peak mean over the full solution by 1.4 points at 4B and 1.6 at 8B, while storing an order of magnitude fewer hint tokens. Comparisons across three seeds also show positive mean gains for the framing and category contexts at both scales. Answer-only conditioning remains competitive in the primary runs, within 0.2 points of the full solution at these scales. The preferred context varies with student scale and task. Initial teacher-student KL does not order downstream performance. What a self-teacher should see is therefore not everything it could, but the level of abstraction its student can still act on.

Kanghui Tian, Siyuan Liu, Tianxiang Jiang +8

Fudan University · Shanghai Artificial Intelligence Laboratory · Nanjing University +4

On-Policy Self-Distillation Context Distillation Learning Using Privileged Information

Sep 17, 2026cs.CL

What Does Privileged Information Add to On-Policy Self-Distillation?

On-policy self-distillation (OPSD) lets a language model learn from a frozen copy of itself that sees an answer or a worked solution. Giving the teacher this extra information seems to offer the student more to learn, but how much does it add beyond distillation itself? To isolate that contribution, we construct AMPLE-Math, a reusable suite of 5,319 mathematical problems with six reasoning views that share the same answer, and compare each view with matched reference-free distillation. With a thinking-enabled teacher supervising direct-response rollouts, reference-free distillation accounts for much of Qwen3-1.7B's improvement under thinking-enabled evaluation, both in domain and on external benchmarks. Evidence for an additional reference benefit is modest in Qwen, strongest for a polished solution, whereas complete traces add two percentage points in SmolLM3-3B at step 50. These benefits depend on the student being trained. At the same checkpoint, replacing short direct-response rollouts with long thinking-enabled rollouts turns gains into losses in both families while the problems, references, and evaluation stay fixed. Teacher profiles and matched loss interventions in Qwen further show that changing token-level supervision can leave student behavior largely unchanged. Together, these findings suggest that OPSD can improve access to existing reasoning capabilities through parameters shared by direct-response and thinking-enabled inference. The value of a privileged reference is what it adds to this cross-mode transfer, not how much of the solution it reveals.

XiuYu Zhang, Wei Chow, Junfeng Fang +2

National University of Singapore

On-Policy Self-Distillation Learning Using Privileged Information LLM Reasoning

Sep 14, 2026cs.CL

Mind2Dialogue: Training Human-Aware Language Models by Simulating User Mental States

As language models become more capable, long-term collaboration in learning, reasoning, and decision-making calls for a deeper understanding of the people they serve. Yet training such human-aware language models faces a fundamental supervision gap because current datasets for LLM assistant training contain few if any well-informed responses explicitly grounded in users' unspoken beliefs and goals. Scaling such supervision is inherently constrained, as users' underlying states are not directly observable. We thus propose the Mind2Dialogue framework to mitigate this gap by simulating users' mental states and turning them into privileged supervision for human-aware training. Specifically, we first propose a psychology-guided simulator that preserves personal characteristics while updating mental states through interaction to generate coherent conversations. The key idea is to enforce a shared evolving mental state that drives user behavior and guides an Oracle assistant's responses. Our privileged distillation then trains models on the Oracle's well-informed responses to assist users without direct access to their mental states at deployment. Moreover, we propose to evaluate human-aware learning by combining personalization and theory of mind, examining how models understand people and act on that understanding. Training on the full Mind2Dialogue corpus improves every reported personalization metric over the corresponding Qwen, Llama, and OLMo instruction-tuned baselines, including gains of 26.6 to 40.9 percentage points in preference-following generation. The gains extend to belief and action reasoning on Qwen and Llama, beyond personalized assistance. Looking forward, Mind2Dialogue makes user simulation a foundation for genuine AI collaborators that understand beliefs and intentions behind people's words and support their long-term goals across education, work, and everyday life.

Zixuan Wang, Yufan Zhou, Jinzhou Tang +16

UC San Diego · KU Leuven · Johns Hopkins University +2

LLM Personalization Theory of Mind Personality Modeling in Language Models Learning Using Privileged Information User Simulation

Sep 14, 2026cs.LG

SCOPE-OPSD: Fisher-Conditioned Privileged Subspaces for On-Policy Self-Distillation

On-policy self-distillation (OPSD) scores student-generated prefixes with a solution-conditioned self-teacher, yet transfers supervision only through next-token probabilities. We ask whether the aligned final-layer discrepancy offers a useful second channel, and how to test that channel without confusing its geometry with auxiliary strength. SCOPE-OPSD projects the privileged teacher-student residual onto a frozen rank-64 factor estimated from residual covariance and language-model-head Fisher sensitivity. It reuses the forwards already required by OPSD and adds neither rollouts nor inference-time modules. A matched Random control preserves the structured factor's rank and nonzero spectrum and uses per-arm gradient-RMS calibration, isolating the effect of the data-dependent orientation. Across the complete 25/50/75/100-step trajectories for Qwen3-1.7B, 4B, and 8B, Structured is never below Pure OPSD, with strict gains in 11 of the 12 model-checkpoint combinations and an exact tie at 4B step 25. Structured also exceeds matched Random in 10 of the 12 combinations. At step 75 on Qwen3-1.7B, Structured exceeds matched Random by 1.39 Macro Avg@12 points in each of two independent training reruns. A cross-fitted diagnostic also shows 4.40 times greater held-out privileged-gap capture than the matched random orientation. The results support a compact, Fisher-conditioned privileged subspace for short-budget OPSD.

Yunmeng Chen (Chongqing Ant Consumer Finance Co., Ltd), Kunyu Wang (Alibaba Cloud Computing Co. +18

Chongqing Ant Consumer Finance Co., Ltd. · Alibaba Cloud Computing Co., Ltd. · Chongqing University of Posts and Telecommunications

On-Policy Self-Distillation Language Model Distillation Learning Using Privileged Information Knowledge Distillation

Sep 14, 2026cs.LG

Quantifying the Value of Privileged Information Using a PAC-Bayesian Approach

In practice, various learning scenarios provide access to auxiliary features exclusively during training. Incorporating such data to enhance model performance gave rise to a paradigm known as Learning Using Privileged Information (LUPI). While this extra information is intended to improve the resulting model, establishing a generalized, cohesive understanding of how privileged information (PI) transfers useful knowledge remains a challenge. Vapnik's original theory and subsequent works offer performance guarantees in certain cases, but these results are inherently per-algorithm and rely on setting-specific proof approaches. Consequently, a more general framework explaining how and when PI transfers useful knowledge is still missing. To bridge this gap, we introduce an algorithm-agnostic, information-theoretic approach based on the PAC-Bayes framework. Rather than asking whether a particular algorithm exploits PI, we ask how much value it could offer: comparing the tightest achievable risk bound with and without PI yields its potential - an upper limit on the extractable gain. We introduce a metric that quantifies this potential directly from empirical training risk, bypassing the need for test-time data access, and validate our findings in both supervised and unsupervised settings. The results demonstrate a robust correspondence between our training-time metric and true test-time performance gains. Ultimately, this work takes a necessary step toward an information-theoretic understanding of LUPI, and quantifying the potential of privileged features before committing to a model.

Vasily Bokov (aQa, Leiden University, The Netherlands +24

Value of Information Learning Using Privileged Information

Sep 2, 2026cs.CV

Learning to Track from Privileged Target Appearances

Target templates define what a visual tracker searches for, yet the templates available at inference trade off localization certainty with appearance freshness: the initial ground-truth template is exact but becomes stale, whereas recent templates better reflect the current appearance but are cropped from uncertain predictions. We quantify this bottleneck with a non-deployable oracle that supplies an exact current-frame target crop, improving AUC on LaSOT by 15.2 percentage points. This gap reveals a training-only opportunity: frame-level ground truths provide exact current- and future-frame target crops, although such crops are unavailable at deployment. We introduce Privileged Appearance Transfer for Tracking (PATT), a teacher-student training framework that transfers these privileged appearances to a deployable tracker through multi-level representation prediction. The privileged teacher observes exact target crops from past, current, and future frames, whereas the student receives only past-frame templates and learns to predict the teacher's search representations. To avoid transferring unreliable teacher signals, PATT weights this transfer by the teacher's relative localization advantage over the student and its absolute localization accuracy. After training, the teacher, latent predictor, reliability weights, and privileged crops are removed, leaving standard student-only inference. Across seven benchmarks at two model scales, PATT achieves consistent gains under both long- and short-term tracking protocols.

Xin Chen, Jiao Xu, Dong Wang +2

City University of Hong Kong · Dalian University of Technology

Visual Object Tracking Learning Using Privileged Information

Aug 31, 2026cs.RO

SleepWalking: Privileged Representation Shaping for End-to-End Blind Locomotion in Legged Robots

Partially observable locomotion requires a policy to act when task-relevant properties of the robot--environment state are not fully specified by instantaneous observations. Existing approaches often address this challenge by explicitly estimating missing physical variables or processing extended observation histories through structured architectures. We take a different view: partial observability is fundamentally an information-retention problem. The decisive question is not how task-relevant information enters the network, but whether the policy's internal state retains it. Guided by this perspective, we propose SleepWalking for Robot Locomotion (SWAQ), a one-stage end-to-end framework that uses next-step privileged physical reconstruction to shape what a recurrent history representation retains during policy learning, while the deployed actor uses only a direct history-to-action pathway. Under aligned training settings, SWAQ achieves a 15.0% higher peak mean terrain level than DWAQ, the strongest non-exteroceptive baseline, while using 44.4% fewer inference MACs per control step. Layerwise probes further show that information associated with the reconstructed physical variables remains linearly decodable through the policy head up to the layer preceding the action output. Complementary theoretical analysis relates privileged-variable recoverability to the achievable-return gap between history-based and privileged-information policy classes. These results suggest that semantic objectives can structure learning without requiring a corresponding architectural decomposition of the deployed controller.

Zheng Pan, Tenghui Wang, Peilin Li +5

Northwestern Polytechnical University, Xi’an 710072, China · Shanghai Jiao Tong University, Shanghai 200240, China · Yunmu Intelligent Manufacturing Co., Ltd., Jiangsu 215400, China

Robot Policy Learning Partially Observable RL RL for Legged Locomotion Learning Using Privileged Information

Aug 10, 2026cs.LG

Distill Skills into Weights, Not Prompts: Abstract Skills as Privileged Signals for On-Policy Self-Distillation

Reinforcement learning with verifiable rewards yields no group-relative signal when rollout groups are uniformly correct or uniformly wrong, which account for 63.0-68.0% of groups in our experiments. We propose SKALD (Skill-Anchored Latent Distillation), an on-policy self-distillation framework that uses two context views of the same Qwen3-Base model: a question-only student and a teacher conditioned on an abstract, explicit-answer-filtered skill card. The student is trained on its own prefixes, transferring the skill-induced advantage into shared parameters without privileged input at test time. To stabilize context-induced distribution mismatch, SKALD employs an annealed exponentially tilted objective that downweights teacher-preferred tokens with very low student likelihood; as the tilt vanishes, it converges to teacher cross-entropy and recovers the forward-KL student gradient. An empirical gate activates distillation only when verified rollouts estimate a positive teacher advantage. Across five held-out mathematics benchmarks, SKALD improves overall avg@8 over GRPO by +2.46, +4.85, and +12.01 at 0.6B, 1.7B, and 4B, respectively. At 1.7B, zero-variance-only distillation recovers 84.7% of the full gain, while SKALD remains +4.06 above FLOP-matched GRPO and exceeds contextual skill exposure by +3.77. These results show that abstract skills provide dense supervision where group-relative rewards become uninformative.

Yubo Jiang, Fengying Xie, Zhiguo Jiang +1

School of Astronautics, Beihang University, Beijing 102206, China · Longcat Interaction Team, Meituan, Beijing 100102, China · Tianmushan Laboratory, Beihang University, Hangzhou 311115, China

On-Policy Self-Distillation RL for Language Model Reasoning Reinforcement Learning with Verifiable Rewards Learning Using Privileged Information

Aug 10, 2026cs.AI

Privileged Likelihood Is Not Automatically Value: Three Checks for Token Credit in On-Policy Self-Distillation

Outcome verifiers score completed reasoning traces but do not assign credit to intermediate tokens. Privileged self-distillation attempts to fill this gap by rescoring a model's own rollout with training-only information. A token likelihood change, however, is not automatically outcome credit. We separate three questions: whether the score tracks better actions, whether feedback construction changes what is compared, and what behavior the training loss reinforces. We establish these distinctions formally. When a rollout is scored using hindsight feedback written about that same rollout, its content determines both the tokens and the scoring context, creating direct self-dependence. Using feedback from another rollout of the same problem removes this dependence but does not guarantee a useful score. In matched experiments with a 20B model on AIME 2025, the implemented additive score is near chance (AUC=0.505) and slightly favors incorrect traces after length adjustment. In the paired comparison, the outcome-only control records 64.2%, versus 24.2%--33.9% for five token-score variants. The results motivate validating score meaning, feedback construction, and training behavior separately before calling a likelihood signal credit.

Xuan-Phi Nguyen, Shrey Pandit, Yiran Zhao +3

Salesforce AI Research

On-Policy Self-Distillation Token-Level Credit Assignment Step-Level Credit Assignment in RL Self-Distillation Learning Using Privileged Information

Aug 10, 2026cs.LG

Privileged Solutions or Context-Induced Teacher Behavior? Dissecting On-Policy Self-Distillation

On-Policy Self-Distillation (OPSD) is commonly interpreted as the transfer of privileged information: a teacher observes the verified solution to the target problem and supervises the student's trajectory. However, this interpretation conflates two effects. The reference solution not only reveals the answer to the current instance but also changes the context under which the teacher provides token-level supervision. We investigate the role of target-specific privilege with

\mathrm{OP}^{2}\mathrm{SD}

(On-Policy Self-Distillation from Other Problems), which replaces the paired reference with a problem and solution from a different example, while preserving the student rollout, teacher, and distillation objective. Across three models and three mathematics benchmarks,

\mathrm{OP}^{2}\mathrm{SD}

improves over the base model, remains competitive with OPSD. The success of

\mathrm{OP}^{2}\mathrm{SD}

implies that OPSD gains do not necessarily come from access to the reference solution, and that the teacher's context-induced behavior is an important factor.

Yuki Ichihara, Naoto Iwase, Mohammad Atif Quamar +1

Mohamed bin Zayed University of Artificial Intelligence · Nagoya University · RIKEN AIP

On-Policy Self-Distillation Language Model Distillation On-Policy Distillation Learning Using Privileged Information

Aug 6, 2026cs.CV

The Next Screenshot Knows: Gated Hindsight Distillation for Mobile GUI Agents

GUI agents are commonly trained offline from successful interaction trajectories. Standard training decomposes each trajectory into prefix-action pairs: the agent predicts an action from the current screen and interaction history, while the subsequent observation is discarded. This removes the rationale of why an action is correct: the evidence often appears only on the subsequent screen. For example, to enable Soft Wrap, the agent should click Edit or View, but nothing reveals this until the menu opens. Without such evidence, standard imitation gives the model little chance of ever sampling and thus learning the correct reasoning. To address this issue, we propose Gated Hindsight Distillation (GHD), which uses the next screenshot as privileged information during training. A student predicts from the observable trajectory prefix, while a parameter-sharing teacher additionally observes the next screenshot and re-scores the student's on-policy responses. We apply distillation only when the student fails and the hindsight-conditioned teacher recovers the demonstrated action. GHD improves task success over GRPO on AndroidWorld and AndroidLab across two vision-language models. The code and checkpoints will be made available.

Weiwei Li, Junzhuo Liu, Tong Chu +2

University of Electronic Science and Technology of China

GUI Agents Imitation Learning Mobile GUI Agents Learning Using Privileged Information Knowledge Distillation

Aug 5, 2026cs.AI

Privileged, but Biased: How PI-Conditioned Teachers Break Self-Distillation

Self-distillation (SD) has emerged as a compute-efficient alternative to reinforcement learning with verifiable rewards: a self-teacher, conditioned on privileged information (PI) about the answer such as a reference solution, supplies dense per-token supervision to a student that never sees it. Reported gains, however, come almost exclusively from narrow, low-difficulty settings, leaving open a basic question: as a lone objective, with no reward term, does SD teach anything? We reproduce SDPO's reported gains in its easy setting, then apply the identical setup to difficult tasks and find that it does not. Across question answering, mathematics, coding, and multi-turn agentic tool use, across reasoning modes, model sizes, and forms of PI, and under both the SDPO and OPSD recipes, the per-token loss falls steadily while validation accuracy does not improve and typically degrades. We explain this failure through a single causal chain from the loss to the model it produces. The chain begins with PI bias: having seen one particular reference solution, the teacher's per-token target is pulled toward that trajectory rather than toward correctness in general, an effect we quantify with a PI Bias Score. Trained to match this target everywhere, the student's objective becomes nearly blind to whether a rollout is correct, and the loss it assigns falls mostly on low-information tokens like stopwords, punctuation, uncertainty markers, rather than those that determine the answer; within correct rollouts the exploratory tokens incur the highest divergence, so it penalizes the hesitation that reasoning requires. The result is a flatter, less decisive student that is no better at reasoning: as a lone objective, SD optimizes a signal decoupled from task success.

Sarthak Harne, Chinmay Karkar, Yash Pandya +2

Microsoft Research

Language Model Distillation Self-Distillation Learning Using Privileged Information LLM Reasoning

Aug 3, 2026cs.AI

Is More Privileged Information Better? From Solution Traces to Problem-Solving Structure in Self-Distilled Reasoning

On-policy self-distillation (OPSD) improves reasoning by using a privileged view of a model conditioned on reference solutions to supervise a student view that observes only the question. However, the teacher-provided token-level targets may depend on reference-specific information unavailable at inference time. We propose Problem-Space-Guided OPSD (PS-OPSD), which replaces the complete solution with trajectory-grounded guidance describing the initial state, goal conditions, constraints, and a selected state-transition path. The student rollout and OPSD objective remain unchanged. Across three mathematical reasoning benchmarks and model scales ranging from 1.7B to 8B, PS-OPSD achieves the highest aggregate question-only accuracy among the compared methods. Controlled experiments further indicate that guidance relevance and path coherence contribute to these gains, highlighting the representation of privileged information as an important design choice in OPSD.

Xuyang Zhao, Liting Zhang, Zichen Xu +4

1TMCC, College of Computer Science, Nankai University, Tianjin, China · 2Huawei Technologies Ltd., Beijing, China

On-Policy Self-Distillation Knowledge Representation Learning Using Privileged Information LLM Mathematical Reasoning

Jul 31, 2026cs.CV

Distill What RGB Can Recover: Privileged 3D Evidence for RGB-Only Vision-Language Models

3D scene understanding requires reasoning about entity existence, spatial layout, and object relations, yet RGB images alone often provide insufficient 3D cues. Existing 3D-VLMs commonly rely on depth or 3D-position-aware inputs at inference time, introducing additional acquisition, reconstruction, or annotation costs that limit RGB-only deployment. We therefore study how training-time 3D evidence can be converted into spatial reasoning capabilities retained under RGB-only inference. We propose a privileged-evidence distillation framework that constructs a distillable teacher through a unified evidence interface and controlled residual injection, and transfers its knowledge to a deployable student receiving only RGB images and questions through logit and structured representation distillation. To avoid imitating teacher signals unsupported by RGB, we further introduce evidence-sensitivity-guided distillation, which uses corrupted evidence to identify highly evidence-dependent targets and down-weight their supervision. We also define a recoverability decomposition based on the matched baseline, teacher, and student, separating privileged gains into RGB-recoverable improvements and residual teacher advantages. Across four benchmarks, the teacher achieves the best result on 7 of 11 reported metrics among the compared methods. The RGB-only student outperforms its matched baseline on all 11 metrics, including gains of 10.4 ScanQA CIDEr and 19.1 Scan2Cap [email protected], without additional inference-time inputs. These results validate the effectiveness of training-time privileged 3D evidence distillation for both teacher performance and deployable RGB-only spatial reasoning. Separately, our matched baseline-teacher-student analysis characterizes privileged-gain transfer across evidence types and spatial skills.

Yanbin Hu, Jin Cui, Jun Ye +4

School of Software, Xi’an Jiaotong University · School of Artificial Intelligence, Xi’an Jiaotong University · State Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University +1

3D Spatial Reasoning VLM Distillation Learning Using Privileged Information 3D Scene Understanding 3D VLMs

Jul 21, 2026cs.CV

Privileged Lesion-Context Relational Distillation for Mask-Free Skin Lesion Classification

Accurate skin lesion classification can benefit from lesion segmentation masks, but requiring masks or an auxiliary segmentation model during inference reduces clinical practicality and increases computational complexity. This work introduces Privileged Lesion-Context Relational Distillation (PLCRD), a teacher-student framework that exploits lesion masks exclusively during training while preserving image-only inference. The privileged teacher jointly analyzes the original dermoscopic image and its mask-guided lesion region to learn lesion-specific and contextual diagnostic representations. An image-only student is then trained through complementary knowledge-transfer mechanisms that convey the teacher's diagnostic distribution, lesion-focused attention, inter-lesion relational geometry, and lesion-context structure. PLCRD decomposes deep representations into lesion and contextual embeddings and transfers their relational organization through inter-lesion similarity alignment, lesion-context affinity matching, separation regularization, and class-aware relational learning. This formulation avoids direct feature matching between heterogeneous teacher and student architectures and enables the student to internalize mask-informed diagnostic structure without accessing masks at deployment. The framework was evaluated on HAM10000 using lesion-disjoint data partitioning and externally validated on ISIC 2018 without retraining. PLCRD achieved a lesion-level macro-F1 of 0.773 +/- 0.018, balanced accuracy of 0.764 +/- 0.023, and macro-AUROC of 0.976 +/- 0.002 on HAM10000, together with a macro-F1 of 0.732 +/- 0.008 on ISIC 2018. The results indicate that privileged lesion annotations can be transformed into transferable relational knowledge, yielding a practical and interpretable approach to mask-free skin lesion classification.

Abu Mukaddim Rahi, Md Mithun Hossain, Md Zulficar Hasan Joy +2

Department of IT in Artificial Intelligence, Victoria University, Footscray, VIC, Australia · BUBT Resarch Graduate School, Bangladesh University of Business and Technology, Dhaka, Bangladesh · Department of Artificial Intelligence, Daffodil Institute of Information Technology, Dhaka, Bangladesh +2

Skin Lesion Classification Medical Image Classification Relational Knowledge Distillation Learning Using Privileged Information

Jul 19, 2026cs.AI

Bridging the Information Gap: Semantic Densification and Hindsight Distillation for Cold-Start Prediction

New-user cold-start is a critical bottleneck for e-commerce platforms: predicting user lifetime value (LTV) and conversion rate (CVR) for users with sparse interaction history. Two prior directions -- LLM-based semantic augmentation and learning using privileged information (LUPI) -- each face a key limitation. First, LLM augmentation produces unstructured rationales that are noisy and hard to operationalize in production. Second, naive student-teacher distillation can be brittle due to an information gap between the privileged teacher and the sparse student; moreover, this gap is heterogeneous across users. We propose SemRaD, a Semantic Reasoning-aware Distillation framework addressing both limitations. First, a Structured Semantic Reasoning Pipeline replaces free-form rationales with a structured schema built via a discover-curate-audit workflow, producing per user a Densified Semantic Profile (consumed by the deployed student via a Semantic-Gated Encoder that focuses on the most informative dimensions) and a Hindsight Distillation Target reconciled from pre- and post-conversion reasoning (used only at training). Second, to bridge this gap and handle its heterogeneity, a Hindsight-Aware Distillation Network transfers privileged knowledge via the hindsight target, with Distillation Experts improving transfer under per-user variability. On a large-scale industrial dataset, SemRaD lifts +1.9% LTV (Gini) and +1.0% CVR (AUROC) over a production-grade base; a four-week online A/B at Keeta confirms +1.0% LTV / +0.43% CVR. SemRaD also matches the production system's LTV using only 9% of the training data while improving CVR by 0.8%.

Hao Duong Le, Yifei Gao, Huan Li +4

Tsinghua University Beijing, China · Meituan Beijing, China

Cold-Start Recommendation User Modeling Learning Using Privileged Information Knowledge Distillation Tabular Prediction

Jul 17, 2026cs.CV

IoU-PD: IoU-Aware Privileged Distillation for Visual Grounding with Multimodal Large Language Models

Visual grounding with multimodal large language models is commonly formulated as autoregressive coordinate generation, where a model outputs bounding-box coordinates as text given an image and a referring-expression prompt. While this interface is simple and compatible with instruction following, it introduces a mismatch between training and evaluation: training optimizes token-level likelihood over coordinate strings, whereas grounding quality is measured by geometric overlap. We propose IoU-PD, an IoU-aware privileged distillation method for coordinate-generating multimodal large language models. IoU-PD uses ground-truth boxes not only as coordinate targets, but also as privileged training-time guidance. During training, the student receives the original image and prompt, while a frozen teacher receives a box-marked image and an augmented prompt that indicates the marked region. The student is trained with a supervised fine-tuning anchor and a privileged distillation loss whose token weights reflect both geometric importance and teacher reliability. At inference time, IoU-PD requires no box overlay, privileged hint, teacher branch, or additional prediction module. Experiments on standard referring-expression grounding benchmarks show consistent region-level improvements over strong coordinate-generating baselines, demonstrating that ground-truth boxes can provide useful privileged guidance beyond serving as coordinate labels.

Xiuyuan Zhu, Ke Lu, Hao Wu +4

University of Chinese Academy of Sciences, Beijing, China · State Key Laboratory of Communication Content Cognition, Beijing, China · Peng Cheng Laboratory, Shenzhen, Guangdong, China +1

Cross-Modal Knowledge Distillation Multimodal Large Language Models Vision-Language Grounding Visual Grounding Learning Using Privileged Information

Jul 13, 2026cs.CV

Anatomy-Privileged Distillation with Token Routing for MRI-Based Prediction of Perineural Invasion

Perineural invasion (PNI) is associated with poor postoperative outcomes in intrahepatic cholangiocarcinoma, but it is confirmed by surgical pathology. Existing preoperative imaging models often rely on radiologist-defined variables, contrast-enhanced imaging, or manual annotations. We propose an anatomy-privileged teacher--student framework for patient-level PNI prediction from T2-weighted MRI. During training, the teacher uses MRI with tumor and liver masks to learn dense token routing, and the student distills this guidance to retain and aggregate informative tokens under a fixed budget. Anatomical supervision is restricted to training, and the deployed model does not require masks at inference. In 155 patients, the proposed method achieved the highest mean AUROC of 0.750 among matched MRI-only baselines evaluated under the same protocol, with 1.43 GFLOPs and 8.02 ms per case on a Jetson Orin Nano Super Developer Kit.

Hyunsu Go, Youngung Han, Kyeonghun Kim +15

Seoul National University, Seoul, Republic of Korea · OUTTA, Seoul, Republic of Korea · Kyung Hee University, Seoul, Republic of Korea +5

Medical Image Classification Clinical Prediction Oncology Learning Using Privileged Information Knowledge Distillation

Jul 9, 2026cs.CV

Mixture of Probes: Learning from Privileged Modalities in Multimodal LLMs Through Probing

Multimodal Large Language Models (MLLMs) are typically designed under the assumption that all modalities available during training will also be accessible at inference. However, many real-world settings violate this assumption, requiring models to operate under a privileged modality setting, where auxiliary modalities are available only during training. While these modalities contain valuable information, existing MLLMs largely fail to leverage them effectively, as they treat modalities as interchangeable inputs rather than sources of complementary supervision. We propose Mixture of Probes (MoP), a novel framework that disentangles modality-specific and modality-general signals within the MLLM, allowing the model to preserve modality-dependent structure while learning transferable representations across modalities. At its core, MoP achieves this through a structured probing mechanism that extracts and organizes information from intermediate representations of a shared modality encoder, rather than relying only on final-layer alignment as done in existing MLLMs. To support this disentanglement, we further introduce MoP Cross-modal Training (MoP-X), a training strategy for MoP centered around a probe disentanglement loss that prevents probe collapse and encourages cross-modal learning. We evaluate MoP across two domains spanning eight tasks and four modalities under a comprehensive evaluation protocol tailored to the privileged modality setting, where each modality is independently treated as the sole input at inference time. MoP consistently outperforms strong MLLM baselines, achieving up to 65% relative improvement, demonstrating that auxiliary modalities, even when unavailable at inference, can provide substantial gains when effectively leveraged during training. Code, model checkpoints, and evaluation protocols will be made available at https://github.com/Sony/MoP.

Dominick Reilly, Qiyu Wu, Hiromi Wakaki +2

Sony Group Corporation · University of North Carolina at Charlotte · Sony AI

Missing-Modality Learning Cross-Modal Representation Learning Multimodal Large Language Models Multimodal Foundation Models Learning Using Privileged Information Multimodal Understanding

Jul 6, 2026cs.AI

Rethinking On-Policy Self-Distillation for Thinking Models

Self-distillation is a promising recipe for self-improvement in language models. In this setting, a model can serve as its own teacher when given privileged information, such as a solution to a math problem. This seems especially appealing for thinking models, which can use test-time reasoning to absorb the privileged information. Surprisingly, we show that privileged self-distillation degrades thinking models on long reasoning traces: across five Qwen3 and OLMo thinking models evaluated on AIME24, AIME25, and HMMT25, privileged-context distillation causes a relative drop of up to 17% in avg@16 accuracy. The degradation scales with the amount of privileged context withheld from the student and is most pronounced at long rollout budgets, where thinking models otherwise obtain their largest gains. This failure mode is not specific to self-distillation: on-policy distillation (OPD) improves thinking models, but privileged OPD reverses these gains. Our diagnostics link this failure mode to how privileged teacher context reshapes learning at high-entropy forking positions, where multiple continuations remain plausible and may lead to different reasoning paths. Privileged context lowers fork rates in thinking-model rollouts but not in instruction-model rollouts. This leads to an interesting dichotomy, where privileged context can help instruction-tuned models but hurts stronger thinking models. The effect is visible when the student begins a self-correction branch, where privileged OPD penalizes sampled reconsideration tokens that vanilla OPD supports. Thinking models trained with a privileged teacher produce fewer verification, backtracking, and hedging markers, even after length normalization. These findings indicate that self-distillation for strong thinking models requires attention to token-level signal, especially around correction and reasoning steps.

Simran Kaur, Narutatsu Ri, Yinghui He +2

Princeton Language and Intelligence, Princeton University

LLM Self-Correction On-Policy Self-Distillation On-Policy Distillation Context Distillation Learning Using Privileged Information Large Reasoning Models

Jul 1, 2026cs.CV

How Much Future Helps? A Controlled Study of Future-Privileged Supervision for Causal Egocentric Gaze Estimation

Egocentric gaze estimation is commonly studied using models that process the full video with access to future frames, while real-world applications require strictly causal, online prediction. This discrepancy raises key questions: Does future context inherently provide valuable signals for gaze estimation? If so, how much future look-ahead optimally supervises a causal model during training? To investigate, we propose a controlled framework featuring a future-aware branch that accesses a tunable look-ahead horizon during training but is discarded at inference. This design isolates the impact of future context while keeping the inference architecture fixed and strictly causal. Across EGTEA Gaze+ and Ego4D, we find that future-privileged supervision consistently improves causal gaze prediction, confirming its utility. However, performance gains do not increase monotonically with longer look-ahead, but rather peak within a bounded temporal regime. Specifically, optimal performance corresponds to roughly 1.7--3.3 seconds of future context (

H{\in}[5, 10]

) on EGTEA Gaze+ and 2.7 seconds (

H{=}10

) on Ego4D. Our results demonstrate that lightweight causal models can effectively absorb future-aware signals, providing practical guidance for real-time egocentric gaze modeling.

Jia Li, Wenjie Zhao, Fnu Atisri +5

The University of Texas at Dallas · University of Washington · University of Wisconsin–Madison

Gaze Estimation Egocentric Vision Learning Using Privileged Information

Jun 22, 2026cs.CL

PRIDE: Privileged Information-enhanced Distillation for Empathetic Dialogue Generation

Large language models have demonstrated significant capabilities in generating diverse and context-aware responses for empathetic dialogue. However, their computational demands severely limit their deployment in resource-constrained environments. While knowledge distillation offers a promising compression solution, it often fails to transfer the nuanced understanding essential for empathy, as it overlooks the implicit contextual cues that guide human connection. To bridge this gap, we propose a \textbf{pr}ivileged \textbf{i}nformation-enhanced knowledge \textbf{d}istillation method for \textbf{e}mpathetic dialogue generation (PRIDE). Our method leverages privileged information, such as expert psychological annotations or future event summaries, which is available exclusively during training but unavailable at inference time. This allows us to transfer the teacher model's empathetic reasoning to smaller models without relying on extra inputs during deployment. Specifically, PRIDE has three key components: (1) An empathy-reasoning prompt that guides the teacher to explicitly decompose the empathetic process into understanding feelings and analyzing situations step-by-step; (2) A multi-source attention mechanism that directs the student to effectively integrate privileged information; (3) A dual-alignment loss that combines reversed Kullback-Leibler divergence and maximum mean discrepancy to ensure robust knowledge transfer at both logit and feature levels. Experiments on multi-modal and text-only datasets demonstrate that our method achieves competitive performance, and in some cases matches or even surpasses larger teacher models in terms of accuracy and semantic relevance.

Jiaqiang Wu, Zhouan Zhu, Shangfei Wang

Anhui Robot Technology Standard Innovation Base, School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui 230027, PR China

Language Model Distillation Learning Using Privileged Information Knowledge Distillation Emotion-Aware Dialogue Generation

Jun 20, 2026cs.LG

Sequential Minimal Optimization Algorithm for One-Class Support Vector Machines With Privileged Information

One of the powerful techniques in data modeling is accounting for features that are available at the training stage, but are not available when the trained model is used to classify or predict test data -- the Learning Using Privileged Information paradigm (LUPI). Sequential Minimal Optimization (SMO) methods have been developed for supervised Support Vector Machines (SVM), unsupervised one-class SVM, and SVM with privileged information (SVM+). The missing brick in this research has long been a one-class SVM with privileged information (OC-SVM+). In this paper, we propose an SMO algorithm for OC-SVM+ that significantly outperforms non-sequential algorithms for training the OC-SVM+ model. Its finite-time convergence is established. The experiments show how privileged information affects a descriptive domain in the space of original features. Comparative benchmark tests demonstrate that our algorithm is superior over interior point algorithms.

Andrey Lange, Dmitry Smolyakov, Evgeny Burnaev

Skolkovo Institute of Science and Technology (Skoltech), Moscow 121205, Russia · Federal Research Center ‘‘Computer Science and Control" of Russian Academy of Sciences (FRC CSC RAS), Moscow 119333, Russia · Institute for Information Transmission Problems of Russian Academy of Sciences (IITP RAS), 127994 Moscow, Russia +1

Support Vector Machines One-Class Classification Learning Using Privileged Information

Jun 18, 2026cs.RO

Mind the Privileged-to-Camera Gap: Actor-Centric Sidecar Supervision for Camera-First Open-Loop Waypoint Prediction

Camera-first autonomous-driving models predict future ego waypoints from images, ego-state features, and route commands, but waypoint supervision alone does not explicitly supervise actor-level representations of nearby road users. We study this as supervised representation learning for open-loop waypoint prediction. The deployable model uses multi-view RGB, ego state, and route command at inference. During training, simulator-derived sidecar labels supervise actor grounding, privileged hindsight actor relevance relative to the logged ego trajectory, and selected-actor short-horizon motion; these labels are never inference inputs. We evaluate route-disjoint splits with matched architecture, optimizer, validation criterion, checkpoint selection, and three seeds. A plain waypoint-only RGB baseline obtains 1.815

\pm

0.02 m final displacement error (FDE), and the matched no-teacher non-sidecar RGB control obtains 1.716

\pm

0.02 m. Road-user sidecar supervision (RU-sidecar) reduces FDE to 1.223

\pm

0.01 m, a 32.6% reduction over the plain baseline and 28.7% over the matched no-teacher non-sidecar RGB control. It improves over the plain baseline on 1445/1494 routes and over the matched no-teacher non-sidecar RGB control on 1417/1494 routes. Actor-conditioned slices show gains in all nonempty subsets, including 29.1% reduction for samples with at least four valid sidecar actors and 30.0% when a vulnerable road user is present. Optional simulator-state teacher alignment reaches 1.186

\pm

0.15 m FDE, but higher seed variability makes it secondary. Non-deployable simulator-state diagnostics remain stronger, indicating a privileged-to-camera gap. The evidence is limited to open-loop simulation diagnostics.

Feeza Khan Khanzada, Jaerock Kwon

Department of Electrical and Computer Engineering, University of Michigan-Dearborn, 4901 Evergreen Rd, Dearborn, MI 48128, United States

Representation Learning End-to-End Autonomous Driving Learning Using Privileged Information