Accumulation

Follow this topic Ask about this topic

Momentum

1 paper in the last four weeks, down 75% on the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 16

Sep 20, 2026cs.AI

Total Cost of Agency: Exact Attribution of Memory Injection Cost in Multi-Agent LLM Workflows

Every node in a multi-agent large language model (LLM) workflow retrieves context from memory and injects it into its prompt, where those injected tokens are billed as input tokens at the same per-token price as the system prompt and the user query. Production observability tools report total token cost but do not separate the tokens a node generates from the tokens it is handed, so this component of the bill is invisible to the teams paying it. We introduce the Total Cost of Agency (TCA), a decomposition of multi-agent workflow cost into base prompt, inference, memory injection, miss penalty and context-accumulation components, and an exact attribution method: a two-pass, non-billable token count that measures injected tokens directly rather than estimating them from word-count proxies. On a 200-task enterprise benchmark executed against real model APIs, memory injection accounts for 13.6 percent of the variable cost a compile-time optimizer can act on, about 12 percent of the full billed cost, and its share rises from a structural zero at workflow depth one to 27.6 percent at depth six. Injected tokens grow linearly with depth over the measured range (R^2 = 0.9974, depths two through six); a quadratic fit yields a negative leading coefficient, so the data do not exhibit convex growth at these depths. We show the component is controllable at fixed model tier: reducing the retrieval window capacity from 32 to 2 entries lowers injected tokens by 28.7 percent with an accuracy change within seed-level variation. We report in full that our graph-rewriting transforms are approximately cost-neutral in isolation, that two of the five decomposition terms are zero by construction in this harness, and that total workflow cost is dominated by model tier assignment, which we hold fixed and treat as prior work. Prompt caching is not evaluated; all figures are for the uncached case.

Vivek Kumar Singh, Preeti Priyam, Gautam Bhowmick

Independent Researcher McKinney, TX, USA · Independent Researcher Chicago, IL, USA

Large Language Model Workflows Multi-Agent Workflows Multi-Agent Large Language Model Systems Accumulation Instruction Injection Attacks

Aug 6, 2026cs.LG

Threshold-Based Early Stopping of Accumulations in Neural Networks with Binary Activation

Binary neural networks are very attractive for constrained deployment, enabling small footprint and low-power inference. For binary activations, the dot products become sign-controlled additions or subtractions, but the number of operations is unchanged. Indeed, every neuron or output channel still accumulates all of its input, even though only the sign will be retained, which is often wasteful. As the accumulation progresses, the running partial sum frequently drifts so far from zero that its final sign becomes highly predictable long before the last term is reached; every contribution evaluated after that point changes the value of the sum but not the final output activation. This paper turns this observation into a post-training early-stopping mechanism. We characterize the behavior of the running accumulations on the training dataset and use this information to predict the final sign as soon as possible. No model parameter is retrained. We count the number of operations under an idealized ordering of weights. On VGG11 applied to the CIFAR-10 dataset, the method removes

86.6\%

of the accumulation terms of the deepest convolution for a

0.37

-point accuracy drop, and

25\%

of the full-network arithmetic when used on the three deepest convolutions simultaneously, for a

1.36

-point drop.

Quentin Luquet de Saint-Germain, Massil Ait Abdeslam, Jean Pierre David

Polytechnique Montréal, Department of Electrical Engineering Montréal, Canada

Early Stopping Neural Network Training Neural Network Accumulation

Aug 6, 2026cs.AI

When Self-Evolution Backfires: Pre-Commit Gating against Skill Contamination in LLM Agents

Self-evolving agents accumulate capability by distilling reusable skills from their execution trajectories, but we find this process is not monotonic: past a critical pool size, newly added skills degrade performance instead of improving it. We formalize this capability-contamination phase transition and trace it to a structural cause: once a defective skill enters the decision context, it becomes reference material for distilling later skills, forming cross-round contamination chains. We further show the contamination is structurally irreversible: removing a source skill after the fact cannot erase the flawed reasoning its descendants have already inherited, so post-hoc rollback recovers only a small fraction of the lost performance. This makes skill admission a pre-commit necessity rather than a post-hoc fix, and motivates Verifier-as-Gatekeeper (VaG): a progressive trust hierarchy whose three heterogeneous critics - structural validity, behavioral harmlessness, and semantic consistency - filter each skill individually, coupled with a marginal-gain subset selection that removes combinatorial contamination at the top tier before skills reach the runtime context. On Terminal-Bench 2, unconditional accumulation rises to a peak and then degrades, giving back most of its gains as the pool keeps growing, and post-hoc removal of the culprit skills recovers only a small part of the drop - the empirical signature of irreversibility. In contrast, VaG improves every round, reaching 72% pass@1 with a pool roughly 5x smaller, and its frozen skill pool transfers positively to four other backbones and a second benchmark without re-evolution. Ablations confirm the three critics are complementary and mutually non-substitutable, each intercepting a largely disjoint class of harmful skills.

Linfang Shang, Ming Xu, Yiding Sun +4

Tencent

Self-Evolving Agents Self-Evolution Skills Large Language Model Agents Accumulation Phase Transitions

Aug 3, 2026cs.AI

Magnet: Detecting Cross-Session AI Misuse Through Capability Accumulation

The most capable AI deployments are not single models but ensembles of specialized agents that delegate and act in coordination. This architecture unlocks powerful new capabilities, and it also introduces risks that existing frameworks for monitoring, detection, and mitigation were not designed to address. Most state-of-the-art AI abuse detection literature focuses on single-turn or multi-turn (single-session) threat models. This leaves a critical gap: an attacker can decompose a harmful goal into innocuous-looking units and execute each in isolated agentic sessions. The agent is stateless between conversations, but the attacker is not. This asymmetry allows for cross-session trajectories that are effective at evading detection. Our contributions are twofold. First, we demonstrate cross-session goal decomposition as an evasion technique, showing it may elicit more harmful capability than equivalent single-session or multi-turn attacks. By capability we mean an artifact produced at one step of an objective, evidenced by what an interaction produced (model responses and tool-call results), and composable with capabilities accrued elsewhere into a harmful whole. Second, we propose Magnet: an efficient and robust detection approach that models relevant capabilities accrued over time and across agentic conversations, aggregated at a higher-level correlator (in this case, a user ID) rather than per-conversation state. The main challenge is assembling the evidence bundle Magnet reasons over. The incriminating artifacts may be needles scattered through a haystack of benign sessions that are individually harmless, dangerous only once collected. Rather than searching the haystack straw-by-straw (i.e. per-session inspection), Magnet does what its name implies: it attracts the relevant needles out of the hay, across sessions and across time, into a compact evidence bundle a detector can act on.

Natalie Isak, Matthew Dressman

Artificial Intelligence Detection Artificial Intelligence Deployment Evasion Accumulation Magnetic Tunnel Junction

Aug 3, 2026math.OC

Non-KKT Accumulation in Entropic Mirror Descent

For mirror descent generated by a Legendre kernel, perhaps one of the most basic question in optimization is this: must every accumulation point of a bounded mirror descent sequence be Karush--Kuhn--Tucker (KKT) stationary under proper stepsizes? We show that the answer is no. A longstanding obstacle to resolving this question is the boundary blow-up of the Legendre gradient: it keeps every mirror step in the interior, while at a boundary limit, the inverse entropy metric vanishes on active coordinates and can erase the dual-feasibility in the KKT system. We construct

C^\infty

objectives and bounded sequences generated by the Shannon-entropic mirror descent on the nonnegative orthant

\R_+^n

, for every

n\geq 3

, and on the probability simplex

Δ_n

, for every

n\geq 4

, such that, in each case, the set of accumulation points is a smooth boundary circle containing a nonempty relatively open arc of non-KKT points. The steps satisfy

α_k\asymp k^{-β}

with

β\in(1/2,1)

, the objective values are nonincreasing, and the objectives are entropy-relatively smooth. Hence the pathology stems from the degeneracy of the Bregman geometry at the boundary, rather than from failure of descent, or improper stepsizes. To the best of our knowledge, these provide the first counterexamples to KKT accumulation for bounded mirror descent sequences with nonincreasing objective values.

Kuangyu Ding, Kim-Chuan Toh

School of Industrial Engineering, Purdue University, West Lafayette, IN 47907, USA. · Department of Mathematics and Institute of Operations Research and Analytics, National University of Singapore, Singapore 119076.

Mirror Descent Descent Objective Functions Accumulation Bifurcation

Jul 29, 2026cs.LG

From Interface to Inference: Eliciting Any-Order Inference from Any-Order Models

Many discrete reasoning tasks, such as code generation, are inherently non-causal: programmers move between high-level structure and local details, a process we call any-order inference. For autoregressive language models, which lack a native any-order interface, non-causal abilities such as infilling and next-edit prediction require hand-designed mechanisms. Can we instead design models that natively support any-order inference? Masked diffusion models have recently emerged as compelling candidates, as their any-order training objective naturally offers an any-order prediction interface. This interface, however, does not automatically yield any-order inference. We demonstrate that this interface-inference gap stems from positional uncertainty: fixed-canvas, token-level models may know what semantic component should appear without knowing where to place it. In light of this, we propose two complementary approaches: (1) Insertion-based masked diffusion, building on FlexMDM (Kim et al, 2025), relaxes fixed-position commitments via insertions, enabling generation across non-contiguous regions. (2) Latent-space masked diffusion shifts prediction to coarser semantic segments, enabling search over latent generation orders. Empirically, we train a 7B FlexMDM for Python coding and a 125M LatentMDM for GSM8K and show that both approaches induce distinct any-order inference behaviors and improve downstream performance. We release our codebase at https://github.com/SeunggeunKimkr/genuine-any-order.

Seunggeun Kim, Jaeyeon Kim, Taekyun Lee +4

University of Texas at Austin · Harvard University

Masked Diffusion Language Models Autoregressive Language Models Code Generation Accumulation

Jul 21, 2026cs.AI

Black-Mamba: Biologically-Inspired Leaky Accumulation for Conceptual Knowledge under Distribution Drift

Forecasting under real-world conditions is inherently non-stationary, as the conditional distribution of future observations evolves over time. Recent test-time adaptive sequence models address this challenge by updating internal states during inference, but tie adaptation to instantaneous prediction errors or surprise. This coupling can conflate persistent distribution shift with stochastic innovations, leading to unnecessary updates and inefficient adaptation. We introduce Black-Mamba, a test-time adaptive forecasting architecture that formulates online adaptation as evidence-gated state tracking under distribution drift. The model augments a base predictor with a dynamic memory updated when temporally accumulated surprisal provides sufficient evidence of a regime change. This turns adaptation into a selective, event-driven process rather than a continuous one. Across multiple forecasting benchmarks with non-stationary dynamics, Black-Mamba achieves competitive or improved predictive performance compared to existing test-time adaptation methods while significantly reducing the number of memory updates during inference. Together with mathematical analysis and biological evidence, these results suggest that accumulated surprisal provides a principled signal for distinguishing persistent drift from transient noise, yielding more efficient and robust adaptation.

Giuseppe Soriano, Nicola Tonellotto, Alberto Gotta

University of Pisa National Research Council (CNR) Pisa, Italy · University of Pisa Pisa, Italy · National Research Council (CNR) Pisa, Italy

Stable Test-Time Adaptation Non-Stationarity Forecasting Backbone Accumulation Lfsr-Based Stochastic Leaky Integrate-And-Fire Neuron

Jun 29, 2026cs.AI

Why Solve It Twice? Hierarchical Accumulation of Skills for Transfer-Efficient ML Engineering

ML engineering agents waste compute rediscovering known techniques because every competition is a cold start. We present HASTE, a hierarchical multi-agent system that organizes cross-competition knowledge into three scope tiers (global, domain, and competition-specific), each coupled to a matching agent level. An orchestrator coordinates domain specialists and promotes learning between tiers via LLM-driven abstraction. A controlled ablation provides evidence for scoped loading: holding a 159-skill inventory constant across 8 competitions, tiered loading achieves a 100% medal rate while flat loading reaches only 62.5%, the same medal rate as loading no skills, and consumes 2x the output tokens. On the full MLE-Bench Lite benchmark (22 Kaggle competitions), HASTE reaches a medal rate of 77.3% using Claude Sonnet 4.6 at 12h per competition; this is a single-seed campaign result, and multi-seed replication is the priority follow-up. In a cold-start run, the system begins with no accumulated skills. In warm-start runs, it reloads skills learned from earlier competitions, using only global and domain-level skills for transfer across competitions. Warm starts use 52% fewer refinement iterations, and the fraction of proposed changes kept by the agent rises from 42% at low inventory to 85% once 50+ skills are available. These results suggest that better knowledge organization can partly substitute for model strength and compute budget in ML-engineering agents.

Yongbin Kim, Yashar Talebirad, Osmar R. Zaiane

Department of Computing Science, University of Alberta, Edmonton, Canada · Alberta Machine Intelligence Institute (Amii), Edmonton, Canada

Mle-Bench Lite Skills Multi-Agent Communication Accumulation Cold-Start

Jun 15, 2026cs.CL

TokenPilot: Cache-Efficient Context Management for LLM Agents

As LLM agents are deployed in long-horizon sessions, context accumulation drives up inference costs. Existing approaches utilize text pruning or dynamic memory eviction to minimize token footprints; however, their unconstrained sequence mutations alter layouts, introducing prefix mismatches and cache invalidation. This reveals a critical trade-off between text sparsity and prompt cache continuity. To address this, we present TokenPilot, a dual-granularity context management framework. Globally, Ingestion-Aware Compaction acts as a framework harness to stabilize prompt prefixes and eliminate open-world environmental noise at the ingestion gate. Locally, Lifecycle-Aware Eviction monitors the ongoing residual utility of context segments, enforcing a conservative batch-turn schedule to offload content segments only when task relevance expires. Experiments on PinchBench and Claw-Eval under both isolated and continuous modes demonstrate that TokenPilot reduces costs by 61% and 56% in isolated mode, and 61% and 87% in continuous mode, while maintaining competitive performance compared to prior systems. TokenPilot has been integrated into LightMem2 at https://github.com/zjunlp/LightMem2.

Buqiang Xu, Zirui Xue, Dianmou Chen +12

1Zhejiang University · University of Electronic Science and Technology of China · 3Xi’an University of Electronic Science and Technology +1

LLM Inference Optimization Large Language Model Memory Large Language Model Agents Compaction Accumulation

Jun 2, 2026cs.CV

Beyond Encoder Accumulation: Measuring Encoder Roles in Multi-Encoder VLMs

As foundation models scale toward fusing more heterogeneous visual streams, understanding how diverse encoders interact under joint training becomes a prerequisite for principled design. Yet large vision-language models (LVLMs) currently lack the tools to do so, and parameter-efficient encoder configurations remain hard to identify before training. To re-examine encoder roles under joint training, on the 16-benchmark Cambrian-1 suite we retrain and evaluate all 31 non-empty subsets of five common vision encoders under a unified pipeline (~20k GPU-hours total), and report three findings. First, retraining each subset from scratch reveals encoder rankings that differ from those obtained by masking encoders on a fixed checkpoint, including which encoder ranks first overall. Second, we decompose each encoder's contribution into two axes, Capacity, the score an encoder reaches on its own, and Necessity, the drop when it is removed from the full pool. The two axes are not interchangeable. Pairing the two highest-Capacity encoders is suboptimal, while pairing a high-Capacity anchor with an adaptive complement matches the full five-encoder model. Adding further encoders beyond this pair yields only marginal gains. Third, at fixed parameter count, per-encoder pre-projector effective rank explains the residual score variation. The strongest pairs combine an anchor whose rank survives joint training with a complement whose rank expands under it, suggesting that higher-rank, less-collapsed projector inputs correspond to a more favorable optimization regime at the encoder-projector interface. Together, the Capacity-Necessity decomposition and the pre-projector rank analysis, along with comprehensive evaluation through retraining, expose a methodological gap in multi-encoder LVLM design, and offer concrete primitives for closing it.

Wei Ding, Yudong Zhang, Ruobing Xie +3

Tsinghua University Beijing, China · Tsinghua University, Tencent Beijing, China · University of Science and Technology Beijing Beijing, China

Vision Encoders Encoders Recent Vision-Language Models Low-Rank Structure Accumulation

Jun 2, 2026cs.LG

KVarN: Variance-Normalized KV-Cache Quantization Mitigates Error Accumulation in Reasoning Tasks

Test-time scaling is a powerful approach to obtain better reasoning in large language models, but it becomes memory-bottlenecked during long-horizon decoding, as the KV-cache grows. KV-cache quantization can help improve this, but current methods are evaluated under prefill-like settings and errors behave differently under autoregressive decoding. We show that in the latter regime, quantization errors accumulate across timesteps, driven primarily by incorrect token scales. We introduce KVarN, a calibration-free KV-cache quantizer that applies a Hadamard rotation followed by a dual-scaling variance normalization across both axes of the K and V matrices. We find that this combination fixes outlying token-scale errors and substantially reduces error accumulation over existing baselines. KVarN establishes a new state-of-theart for KV-cache quantization on generative benchmarks, including MATH500, AIME24 and HumanEval, at 2-bit precision. A vLLM implementation of the KVarN method is available at https://github.com/huawei-csl/KVarN

Lorenz K. Muller, Philippe Bich, Chiara Boretti +3

Huawei

Key-Value Cache Quantization Autoregressive Decoding Accumulation Reasoning Skills

Jun 1, 2026cs.LG

Aligning Data-Driven Predictors with Allocation: A Decision-Focused Approach to Survival Analysis

Machine learning predictors have become essential tools for guiding automated decision making. However, a major misalignment persists: predictive models are typically optimized in terms of standard statistical metrics in isolation from the algorithmic tasks they inform. We highlight this incongruity in the high-stakes domain of organ allocation by demonstrating that any algorithm relying on (even highly accurate) survival predictors optimized for standard metrics -- such as the Concordance index (C-index) -- can yield arbitrarily poor outcomes when used for allocation, failing to guarantee utility better than a uniform random selection. To bridge the gap between survival analysis and policy optimization, we introduce a decision-focused learning approach based on optimizing normalized discounted cumulative gain (NDCG), a mainstay metric in information retrieval. We establish the utility of NDCG in survival analysis by proving that it translates to guarantees on the performance of allocation. Empirically, we propose a bootstrapping approach to optimize the NDCG of existing survival models. Unlike prior work, we also address the challenge of right censorship when evaluating ranking. On historical heart transplant data from the US, our method dramatically boosts the NDCG of baseline models by 50-100%, which translates to tens of thousands of additional life years gained annually when deployed for transplant allocation. We anticipate that our framework will find broader applications in decision making with predictions.

Itai Zilberstein, Ioannis Anagnostides, Tuomas Sandholm

Department of Computer Science, Carnegie Mellon University, Pittsburgh, PA · Additional affiliations: Strategy Robot, Inc., Strategic Machine, Inc., Optimized Markets, Inc.

Survival Predictions Survival Analysis Chronic Kidney Disease Summary Statistics Accumulation

Jun 1, 2026cs.CL

Unveiling the Entropy Dynamics of Chain-of-Thought Reasoning

This paper investigates the entropy dynamics of Chain-of-Thought (CoT) and uncovers a consistent two-phase structure: an Uncertainty Region of exploration transitioning sharply to a Confidence Region of convergence. We demonstrate that the Confidence Region possesses two critical properties: 1) High Reliability -- answers in the confidence region become highly accurate and stable, and 2) High Redundancy -- models generate unnecessary tokens long after reaching the correct answer. These properties unlock more efficient and reliable inference strategies: 1) Early Exit leverages reliability and redundancy to terminate computation safely when returns diminish, and 2)Test-Time Scaling uses the Confidence Region signal to prioritize converged trajectories. To operationalize these insights, we formulate Confidence Region detection as a sequential change-point detection problem, being the first to apply classical change-point methods to monitor CoT reasoning. Using the Cumulative Sum (CUSUM) algorithm, a statistically optimal change-point detector, we develop a training-free framework for real-time inference control. Experiments show our approach establishes a superior Pareto-frontier for early exit. CUSUM achieves 63.06% accuracy with 11.1% token reduction, outperforming DEER and Dynasor by 3.28% and 4.36% in accuracy respectively. For test-time scaling, CUSUM-weighted voting consistently outperforms self-consistency.

Ting Xu, Xu He, Yupu Lu +4

The Chinese University of Hong Kong · Huawei Technologies Ltd · School of Computing and Data Science, The University of Hong Kong

Chain-of-Thought Reasoning Confidence Intervals Accumulation Change-Point Detection

May 21, 2026cs.AI

AMEL: Accumulated Message Effects on LLM Judgments

Large language models are routinely used as automated evaluators: to review code, moderate content, or score outputs, often with many items passing through one conversation. We ask whether the polarity of prior conversation history biases subsequent judgments, an effect we call the accumulated message effect on LLM judgments (AMEL). Across 84,088 API calls to 12 models from 5 providers (OpenAI, Anthropic, Google, DeepSeek, and four open-source models), we present identical test items in isolation or following histories saturated with predominantly positive or negative evaluations. Models shift toward the conversation's prevailing polarity (d = -0.17, p < 10^-53). The effect concentrates on items where the model is genuinely uncertain at baseline (d = -0.36 for high-entropy items, vs d = -0.15 when the baseline is deterministic). Bias does not grow with context length: 5 prior turns and 50 produce the same shift (Spearman |r| < 0.01; OLS slope p = 0.80). And there is a negativity asymmetry: paired per item, negative histories induce 1.52x more bias than positive (t = 13.03, p < 10^-36, n = 2,733). Scaling helps but does not solve it (Anthropic: Haiku -0.22 to Opus -0.17; OpenAI: Nano -0.34 to GPT-5.2 -0.17). Three follow-ups narrow the mechanism. The token probability distribution shifts continuously, not at a threshold. The negativity asymmetry has both token-level and semantic components, though attributing the balance is exploratory at our sample sizes. Position does not matter: five biased turns anywhere in a 50-turn history produce the same shift. The simplest fix for evaluation pipelines is a fresh context per item; when batching is unavoidable, balancing the history helps.

Sid-Ali Temkit

Large Language Model Bias Large Language Model Judges Impact Analysis Accumulation

May 5, 2026cs.LG

CERSA: Cumulative Energy-Retaining Subspace Adaptation for Memory-Efficient Fine-Tuning

To mitigate the memory constraints associated with fine-tuning large pre-trained models, existing parameter-efficient fine-tuning (PEFT) methods, such as LoRA, rely on low-rank updates. However, such updates fail to fully capture the rank characteristics of the weight modifications observed in full-parameter fine-tuning, resulting in a performance gap. Furthermore, LoRA and other existing PEFT methods still require substantial memory to store the full set of frozen weights, limiting their efficiency in resource-constrained settings. To addres these limitations, we introduce Cumulative Energy-Retaining Subspace Adaptation (CERSA), a novel fine-tuning paradigm that leverages singular value decomposition (SVD) to retain only the principal components responsible for 90% to 95% of the spectral energy. By fine-tuning low-rank representations derived from this principal subspace, CERSA significantly reduces memory consumption. We conduct extensive evaluations of CERSA across models of varying scales and domains, including image recognition, text-to-image generation, and natural language understanding. Empirical results demonstrate that CERSA consistently outperforms state-of-the-art PEFT methods while achieving substantially lower memory requirements. The code will be publicly released.

Jingze Ge, Xue Geng, Yun Liu +6

National University of Singapore · Institute for Infocomm Research (I2R), A*STAR · Nankai University +1

Parameter-Efficient Fine-Tuning Methods Pretraining Subspace Peak Memory Accumulation

Date pendingcs.LG

DASH-OPD: Discrepancy-Aware Switching with Hysteresis for On-Policy Distillation

While on-policy distillation (OPD) reduces exposure bias by training student language models on their own rollouts, early student errors in long-horizon agentic scenarios can lead to contexts unfamiliar to the teacher. To improve trajectory quality, recent work on agentic OPD introduces teacher intervention into training rollouts by switching the executor between the student and the teacher. However, existing methods determine how much teacher intervention is needed---but not when. To address this limitation, we propose DASH-OPD (Discrepancy-Aware Switching with Hysteresis for OPD), the first agentic OPD method to perform adaptive, bidirectional executor switching. At each turn, DASH-OPD measures teacher--student discrepancy using a mean log-probability ratio over action tokens. Student-to-teacher ratios on student turns serve as drift signals, while teacher-to-student ratios on teacher turns serve as recovery signals. These signals are accumulated over multiple turns to form drift and recovery evidence, respectively. DASH-OPD switches executors when either type of evidence exceeds its corresponding switching threshold, introducing hysteresis that prevents rapid switching triggered by transient discrepancy fluctuations. Across three benchmarks and two student model sizes, DASH-OPD outperforms five baselines in all 14 task performance comparisons, while requiring the fewest interaction turns in nine of ten efficiency comparisons. Code, models, and training logs are available at https://github.com/Lucian1115/DASH-OPD

Yuchen Xia, Qianguo Sun, Chao Song +3

The Chinese University of Hong Kong · IDEA Research · Emdoor Research Institute

Efficient On-Policy Distillation Uni-Opd Discrepancy Accumulation