Related papers: From Generic Correlation to Input-Specific Credit …

Representation-based retrieval models, so-called bi-encoders, estimate the relevance of a document to a query by calculating the similarity of their respective embeddings. Current state-of-the-art bi-encoders are trained using an expensive…

Knowledge Distillation (KD) can transfer the reasoning abilities of large models to smaller ones, which can reduce the costs to generate Chain-of-Thoughts for reasoning tasks. KD methods typically ask the student to mimic the teacher's…

Knowledge distillation is a technique for improving the performance of a simple "student" model by replacing its one-hot training labels with a distribution over labels obtained from a complex "teacher" model. While this simple approach has…

On-policy self-distillation (OPSD) improves the reasoning performance of large language models (LLMs) by providing dense token-level supervision for on-policy rollouts. However, existing OPSD methods often yield limited gains on in-domain…

Many applications of reinforcement learning can be formalized as goal-conditioned environments, where, in each episode, there is a "goal" that affects the rewards obtained during that episode but does not affect the dynamics. Various…

On-policy distillation (OPD) is a standard tool for transferring teacher behavior to a smaller student, but it implicitly assumes that teacher and student predictions are comparable token by token, an assumption that fails whenever the two…

On-policy distillation (OPD) is a powerful paradigm for model alignment, yet its reliance on teacher logits restricts its application to white-box scenarios. We contend that structured semantic rubrics can serve as a scalable alternative to…

Knowledge distillation (KD) is a well-known method to reduce inference latency by compressing a cumbersome teacher model to a small student model. Despite the success of KD in the classification task, applying KD to recommender models is…

Model distillation has emerged as a prominent technique to improve neural search models. To date, distillation taken an offline approach, wherein a new neural model is trained to predict relevance scores between arbitrary queries and…

On-policy distillation (OPD) trains a student on its own trajectories under token-level teacher supervision, but existing methods are capped by a single-teacher capability ceiling: when the teacher errs, the student inherits the error. OPD…

Extending the effective context length of large language models (LLMs) remains a central challenge for real-world applications. While recent post-training methods have made progress in long-context scaling, they either rely on high-quality…

Recent analyses question whether reinforcement learning (RL) is responsible for strong reasoning in large language models (LLMs). At the same time, distillation and inference-time sampling, including power sampling, have emerged as…

As large language models increasingly mediate firm - customer interactions, firms face a tradeoff: the most capable models perform well but are costly and difficult to control at scale. Existing knowledge distillation methods address this…

Black-box knowledge distillation for large language models presents a strict trade-off. Simple off-policy methods (e.g., sequence-level knowledge distillation) struggle to correct the student's inherent errors. Fully on-policy methods…

Traditional approaches to RL have focused on learning decision policies directly from episodic decisions, while slowly and implicitly learning the semantics of compositional representations needed for generalization. While some approaches…

Knowledge distillation leverages a teacher model to improve the training of a student model. A persistent challenge is that a better teacher does not always yield a better student, to which a common mitigation is to use additional…

Large language models (LMs) beyond a certain scale, demonstrate the emergent capability of generating free-text rationales for their predictions via chain-of-thought (CoT) prompting. While CoT can yield dramatically improved performance,…

Autoregressive video generators are attractive for streaming, long-horizon, and interactive applications, but distilling strong black-box teachers into causal students remains difficult. The student must learn under its own rollout…

Purpose: In curriculum learning, the idea is to train on easier samples first and gradually increase the difficulty, while in self-paced learning, a pacing function defines the speed to adapt the training progress. While both methods…

On-policy knowledge distillation has proven effective for language models, yet its application to vision-language models (VLMs) remains underexplored. We observe that standard on-policy distillation can improve a student's output quality…