arXiv subjects

Tong Che

Publications and source records attributed to Tong Che.

At least 19 recordsLinked to original sources

arXiv2026

Second-Order Muon Done Right: A Principled Marriage of Spectral Geometry and Curvature

Muon's polar update is exact for an unweighted spectral geometry. We introduce GO-MUON, which uses a matched data-dependent geometry and reuses it across several optimization steps. Conditioned on any positive-definite left and right maps, its raw update exactly solves the corresponding weighted spectral oracle; this statement is independent of how the maps are estimated or how recently they were refreshed. For softmax cross-entropy, we quantify when the observed-label backward factor approaches the model Fisher and generalized Gauss--Newton factor. We also show that four-step refresh nearly preserves the tracking delay of slowly changing geometry while increasing stationary factor noise, making lazy geometry a compute--statistics tradeoff rather than a denoising mechanism.

cs.AI↗

arXiv2026

Wait-Free Locks Should Not Fear Later Arrivals

Helping seems to make a lock wait-free: wrap the critical section in an idempotent thunk that any process can finish once the holder stalls. Yet helping protects the system, not the call. An overwritable candidate lets later requests bump one another in sequence, so a call can be forced to help newcomer after newcomer and never return, while point contention never exceeds two. We ask whether a call can instead be charged only for the requests active when it takes its ticket, never for what arrives afterward. We show that the answer is yes. SeniorLock is a deterministic helpable thunk lock in which a call with ticket-time seniority $\beta$ finishes in $O((\beta+1)(T+1))$ local shared-memory steps, where $T$ bounds one thunk's cost, independently of later invocations. We call this guarantee \emph{retrospective wait-freedom}. The same lock doubles as a universal construction we call SeniorObj: it turns any deterministic sequential object whose operations are bounded, concurrently idempotent thunks into a retrospective wait-free one, with no copying of its representation and, when no senior is active, at essentially the native cost of the operation.

cs.DC↗

arXiv2026

Learning with a Single Rollout via Monte Carlo Pass@k Critic

Estimating token-level advantages in reinforcement learning (RL) for language models remains challenging because scaling up episodic experience collection is expensive. The difficulty intensifies for baseline advantage estimation methods, where repeated sampling causes trajectories to diverge into substantially different reasoning prefixes. In this context, RL algorithms such as GRPO prove limited: an outcome reward is too sparse to be attributed to specific actions like intermediate steps, and comparisons across sampled traces are non-trivial because they are heterogeneous. To mitigate both the computational cost of repeated sampling and the difficulty of credit assignment, we study single-rollout proximal policy optimization (SR-PPO) featuring token-level credit assignment in RL for language models. Instead of estimating advantages by normalizing episodic returns within the candidate group, we train a calibrated token-level credit critic using Monte Carlo outcomes from one rollout per prompt. Specifically, we use the critic to predict the Pass@k success probability at the prompt prefix, which is derived from a Pass@1 attempt. This choice yields a more selective learning signal than Pass@1: it discounts easily solved prefixes while prioritizing hard ones whose success probability remains marginal. We show that as $k$ increases, Pass@k converges to a reachability indicator, reflecting whether a prefix can lead to at least one successful continuation. In an explicit state graph, the limit ($k \rightarrow \infty$) can be computed in $O(|V|+|E|)$ time, offering a promising surrogate for direct credit assignment without the need to sample contrastive traces. As an initial validation, SR-PPO exhibits stable learning dynamics, along with consistent gains in Pass@128 success rates on mathematical reasoning benchmarks such as HMMT26 and AIME24.

cs.LG↗

arXiv2026

Greed Is Learned: Visible Incentives as Reward-Hacking Triggers

Deployed agents increasingly act with their reward proxy in view, such as a balance, score, or KPI dashboard. We show that reinforcement learning can make a policy \emph{addicted} to such a visible self-benefit channel. It chases the displayed payoff across held-out domains, sacrifices the true task to do so, and follows the channel wherever we rewrite it, while policies that never saw the channel stay honest. We call this \emph{reward-channel addiction} and study it in \emph{MoneyWorld}, a synthetic sandbox. The addiction can \emph{flip a model's safety alignment}: trained only on innocuous money tasks with no safety content, the model abandons the safe action it otherwise always takes whenever a dashboard pays for an unsafe one, and reverts to safe once the channel is hidden. This learned bribe replicates across model scales and families. Blindly optimizing super-capable, next-generation AI on KPIs or P\&L can be dangerous for alignment. \emph{Greed is learned} when following such a channel pays.

cs.AI↗

arXiv2026

Constitutional Value Potentials: reading and steering internal priority margins in language models

A constitution tells a language model what to value, but little tells us whether it does. Adherence is judged from outputs, and output evidence is most fragile on value conflicts, where what matters is not which value a model mentions but which one it is willing to sacrifice. We provide evidence that this arbitration can be read from activations in a structured margin readout. We introduce Constitutional Value Potentials (CVP). For each value we learn a scalar potential from the hidden state: an internal pressure to preserve that value, supervised not by the prompt but by an independent judge's verdict on which value the model's own response actually preserved. The signed difference of two potentials is a priority margin. A constitutional clause becomes the claim that a margin stays positive, and a single monitor score flags when it does not. The monitor predicts conflict violations with AUROC up to 0.95, beats a strong hidden-state probe, and generalizes to held-out synthetic conflicts across three Qwen2.5 scales. The signal appears as the answer begins, from the prompt tail and first response token. Read this early, the same signal reveals whether an adversarial priority hack has actually pushed the model toward a violation, rather than only whether the prompt looks adversarial. The same directions also support intervention tests: under selected steering settings, moving along a value direction shifts judged trade-offs in the intended direction. Together, these results suggest that some constitution-relevant priorities are accessible as activation-space margins, rather than only as output behavior.

cs.LG↗

arXiv2026

EMBER: Efficient Memory via Budgeted Evidence Retention for Long-Horizon Agents

Long-horizon agents can archive large histories, but future answers still incur retrieval, rereading, and context costs. When retained memory misses answer-relevant evidence, the system must return to larger portions of the raw history. We study budgeted evidence survival: before the query is known, which source evidence should be retained so that it remains recoverable and usable under a fixed retained source-evidence token budget? We instantiate this setting as Budgeted Pre-Query Retention, where memory is written during ingestion and later read without access to the full raw stream. We introduce EMBER, a learned retention policy that constructs a compact, source-backed evidence state. EMBER stores evidence capsules: verbatim source excerpts paired with retrieval keys and update metadata, preserving both grounding and read-time access. Post-query outcome feedback trains the writer to preserve evidence across the ingestion-retrieval-answer chain. On LongMemEval-RR, our LongMemEval-derived retained-evidence protocol, EMBER-14B reaches 0.3017 F1 at the 8192-token retained-evidence comparison point, compared with 0.1765 for the strongest non-EMBER budgeted baseline. Across retained source-evidence budgets, EMBER improves F1, Retain-Recall, and Read-Recall, indicating that long-horizon memory depends on retaining evidence within the budget rather than rereading larger histories.

cs.CL↗

arXiv2026

Reference Feature Atlases for Mechanistic Auditing of Language Models

Auditing a new language model usually means relearning and reinterpreting its internal features from scratch. We propose a reference feature atlas: a sparse feature library trained once on a reference panel and reused for new targets, which attach by fitting only a linear decoder. This yields two complementary views. The atlas channel reads the target on already interpreted panel features, providing a stable coordinate system across models. The residual channel learns features only from what the atlas fails to reconstruct, making "outside the reference panel" an explicit audit signal. We train leave-one-out atlases over five 7-9B instruction-tuned models and audit held-out Mistral and Qwen targets. On three controlled LoRA hidden objectives injected into both targets, the residual channel makes the planted mechanism perfectly controllable at runtime while matched controls stay unaffected and recovers the planted objective as the top-ranked latent across both targets; on Mistral, where the per-target SAE and pairwise crosscoder baselines are retrained for a head-to-head benchmark, both baselines fail to do so. On Qwen-2.5, the same channel additionally reveals a panel-relative political-framing cluster; steering it shifts the audited framing metrics while out-of-domain controls remain unchanged.

cs.AI↗

arXiv2026

Cast a Wider Net: Coordinated Pass@K Policy Optimization for Code Reasoning

Repeated sampling with a verifier is the standard way to allocate test-time compute for code generation, with pass@$K$ as the canonical metric. Yet the standard policy class draws $K$ independent samples from a single answer distribution, so attempts often collapse onto near-duplicate reasoning paths and waste the budget on redundant rollouts. This failure is costly in competitive programming, where many problems admit multiple distinct algorithmic strategies and pass@$K$ requires only one correct attempt. We propose Coordinated Pass@$K$ Policy Optimization (CPPO), which turns pass@$K$ generation into joint exploration over strategies: a planner emits a tuple of $K{=}4$ alternative high-level methods, and a shared solver attempts one solution per method. CPPO trains this joint policy with a multiplicative planner reward, $R_{\mathrm{plan}} = J_\psi \cdot R_{\mathrm{out}}$, assigning credit only to valid strategy tuples that lead to verifier-confirmed pass@$K$ success. Across APPS, CodeContests, and LiveCodeBench-v6, CPPO improves pass@$4$ over direct sampling, planning baselines, planner-only SFT, and pass@$K$-oriented RL under the same $K{=}4$ solver-attempt budget, with statistically significant gains on six of nine model--benchmark cells. The largest single gain is $+0.16$ on Qwen3.5-9B LiveCodeBench-v6 over the strongest baseline, PKPO ($0.588 \rightarrow 0.748$; paired bootstrap, $p < 0.05$).

cs.CL↗

arXiv2026

Reasoning over Precedents Alongside Statutes: Case-Augmented Deliberative Alignment for LLM Safety

Ensuring that Large Language Models (LLMs) adhere to safety principles without refusing benign requests remains a significant challenge. While OpenAI introduces deliberative alignment (DA) to enhance the safety of its o-series models through reasoning over detailed ``code-like'' safety rules, the effectiveness of this approach in open-source LLMs, which typically lack advanced reasoning capabilities, is understudied. In this work, we systematically evaluate the impact of explicitly specifying extensive safety codes versus demonstrating them through illustrative cases. We find that referencing explicit codes inconsistently improves harmlessness and systematically degrades helpfulness, whereas training on case-augmented simple codes yields more robust and generalized safety behaviors. By guiding LLMs with case-augmented reasoning instead of extensive code-like safety rules, we avoid rigid adherence to narrowly enumerated rules and enable broader adaptability. Building on these insights, we propose CADA, a case-augmented deliberative alignment method for LLMs utilizing reinforcement learning on self-generated safety reasoning chains. CADA effectively enhances harmlessness, improves robustness against attacks, and reduces over-refusal while preserving utility across diverse benchmarks, offering a practical alternative to rule-only DA for improving safety while maintaining helpfulness.

cs.AI↗

arXiv2025

Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail

End-to-end architectures trained via imitation learning have advanced autonomous driving by scaling model size and data, yet performance remains brittle in safety-critical long-tail scenarios where supervision is sparse and causal understanding is limited. We introduce Alpamayo-R1 (AR1), a vision-language-action model (VLA) that integrates Chain of Causation reasoning with trajectory planning for complex driving scenarios. Our approach features three key innovations: (1) the Chain of Causation (CoC) dataset, built through a hybrid auto-labeling and human-in-the-loop pipeline producing decision-grounded, causally linked reasoning traces aligned with driving behaviors; (2) a modular VLA architecture combining Cosmos-Reason, a vision-language model pre-trained for Physical AI, with a diffusion-based trajectory decoder that generates dynamically feasible trajectories in real time; (3) a multi-stage training strategy using supervised fine-tuning to elicit reasoning and reinforcement learning (RL) to enforce reasoning-action consistency and optimize reasoning quality. AR1 achieves up to a 12% improvement in planning accuracy on challenging cases compared to a trajectory-only baseline, with a 35% reduction in close encounter rate in closed-loop simulation. RL post-training improves reasoning quality by 45% and reasoning-action consistency by 37%. Model scaling from 0.5B to 7B parameters shows consistent improvements. On-vehicle road tests confirm real-time performance (99 ms latency) and successful urban deployment. By bridging interpretable reasoning with precise control, AR1 demonstrates a practical path towards Level 4 autonomous driving. Model weights are available at https://huggingface.co/nvidia/Alpamayo-R1-10B with inference code at https://github.com/NVlabs/alpamayo.

cs.RO↗

arXiv2025

AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning

Test-time scaling strategies for Large Language Models predominantly rely on either reinforcement learning with sparse outcome rewards or search-based methods guided by static Process Reward Models. However, outcome-based RL often suffers from training instability and sample inefficiency, while static PRMs require expensive step-wise supervision and are susceptible to reward hacking due to distributional shifts. In this paper, we introduce AIRL-S, a unified framework that integrates Adversarial Inverse Reinforcement Learning with Group Relative Policy Optimization. By inferring a dense, step-wise reward model directly from reference trajectories, AIRL-S eliminates the dependency on labeled process data and uses the same learned PRM as both a training signal and a verifier for search-based TTS. Extensive evaluations across eight benchmarks in mathematics, science, and code generation demonstrate that our policy model improves average performance by 9\% over the base model, matching GPT-4o. We further analyze how the AIRL and GRPO objectives complement each other and how the learned PRM transfers across generators and search algorithms, establishing a robust and cost-effective methodology for scaling test-time computation in complex reasoning tasks.

cs.LG↗

arXiv2025

Two Heads are Better Than One: Test-time Scaling of Multi-agent Collaborative Reasoning

Test-Time Scaling has emerged as a powerful method to extend the reasoning capabilities of Large Language Models. However, single-agent TTS faces significant scalability bottlenecks, as excessively long reasoning traces lead to increased inference costs and stability issues caused by context management failures. To address these limitations, we propose leveraging Multi-Agent Systems as a structural upgrade to standard TTS. By decomposing monolithic reasoning chains into distinct, manageable contexts across multiple agents, MAS offers a more robust framework for scaling reasoning. We validate this approach by introducing M500, a dataset comprising 500 high-quality multi-agent, multi-turn collaborative reasoning traces generated via DeepSeek-R1. Through Supervised Fine-Tuning on M500, we enable open-source models to internalize collaborative reasoning patterns and show improved TTS performance in MAS. Furthermore, we propose an adaptive scaling strategy incorporating a ``CEO'' agent to dynamically guide the reasoning process and optimize collaboration depth. Extensive experiments within the AgentVerse framework demonstrate that our fine-tuned models, Qwen2.5-32B-MAS and Phi4-14B-MAS, significantly outperform their base counterparts. Codes are available at https://github.com/jincan333/MAS-TTS.

cs.AI↗

arXiv2025

LoR-VP: Low-Rank Visual Prompting for Efficient Vision Model Adaptation

Visual prompting has gained popularity as a method for adapting pre-trained models to specific tasks, particularly in the realm of parameter-efficient tuning. However, existing visual prompting techniques often pad the prompt parameters around the image, limiting the interaction between the visual prompts and the original image to a small set of patches while neglecting the inductive bias present in shared information across different patches. In this study, we conduct a thorough preliminary investigation to identify and address these limitations. We propose a novel visual prompt design, introducing Low-Rank matrix multiplication for Visual Prompting (LoR-VP), which enables shared and patch-specific information across rows and columns of image pixels. Extensive experiments across seven network architectures and four datasets demonstrate significant improvements in both performance and efficiency compared to state-of-the-art visual prompting methods, achieving up to 6 times faster training times, utilizing 18 times fewer visual prompt parameters, and delivering a 3.1% improvement in performance. The code is available as https://github.com/jincan333/LoR-VP.

cs.CV↗

arXiv2024

Learning Multiple Initial Solutions to Optimization Problems

Sequentially solving similar optimization problems under strict runtime constraints is essential for many applications, such as robot control, autonomous driving, and portfolio management. The performance of local optimization methods in these settings is sensitive to the initial solution: poor initialization can lead to slow convergence or suboptimal solutions. To address this challenge, we propose learning to predict \emph{multiple} diverse initial solutions given parameters that define the problem instance. We introduce two strategies for utilizing multiple initial solutions: (i) a single-optimizer approach, where the most promising initial solution is chosen using a selection function, and (ii) a multiple-optimizers approach, where several optimizers, potentially run in parallel, are each initialized with a different solution, with the best solution chosen afterward. Notably, by including a default initialization among predicted ones, the cost of the final output is guaranteed to be equal or lower than with the default initialization. We validate our method on three optimal control benchmark tasks: cart-pole, reacher, and autonomous driving, using different optimizers: DDP, MPPI, and iLQR. We find significant and consistent improvement with our method across all evaluation settings and demonstrate that it efficiently scales with the number of initial solutions required. The code is available at MISO (https://github.com/EladSharony/miso).

cs.LG↗

arXiv2024

LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning

This paper presents an advanced mathematical problem-solving framework, LLaMA-Berry, for enhancing the mathematical reasoning ability of Large Language Models (LLMs). The framework combines Monte Carlo Tree Search (MCTS) with iterative Self-Refine to optimize the reasoning path and utilizes a pairwise reward model to evaluate different paths globally. By leveraging the self-critic and rewriting capabilities of LLMs, Self-Refine applied to MCTS (SR-MCTS) overcomes the inefficiencies and limitations of conventional step-wise and greedy search algorithms by fostering a more efficient exploration of solution spaces. Pairwise Preference Reward Model~(PPRM), inspired by Reinforcement Learning from Human Feedback (RLHF), is then used to model pairwise preferences between solutions, utilizing an Enhanced Borda Count (EBC) method to synthesize these preferences into a global ranking score to find better answers. This approach addresses the challenges of scoring variability and non-independent distributions in mathematical reasoning tasks. The framework has been tested on general and advanced benchmarks, showing superior performance in terms of search efficiency and problem-solving capability compared to existing methods like ToT and rStar, particularly in complex Olympiad-level benchmarks, including GPQA, AIME24 and AMC23.

cs.AI↗

arXiv2024

Parallelized Spatiotemporal Binding

While modern best practices advocate for scalable architectures that support long-range interactions, object-centric models are yet to fully embrace these architectures. In particular, existing object-centric models for handling sequential inputs, due to their reliance on RNN-based implementation, show poor stability and capacity and are slow to train on long sequences. We introduce Parallelizable Spatiotemporal Binder or PSB, the first temporally-parallelizable slot learning architecture for sequential inputs. Unlike conventional RNN-based approaches, PSB produces object-centric representations, known as slots, for all time-steps in parallel. This is achieved by refining the initial slots across all time-steps through a fixed number of layers equipped with causal attention. By capitalizing on the parallelism induced by our architecture, the proposed model exhibits a significant boost in efficiency. In experiments, we test PSB extensively as an encoder within an auto-encoding framework paired with a wide variety of decoder options. Compared to the state-of-the-art, our architecture demonstrates stable training on longer sequences, achieves parallelization that results in a 60% increase in training speed, and yields performance that is on par with or better on unsupervised 2D and 3D object-centric scene decomposition and understanding.

cs.LG↗

arXiv2024

Learning from Teaching Regularization: Generalizable Correlations Should be Easy to Imitate

Generalization remains a central challenge in machine learning. In this work, we propose Learning from Teaching (LoT), a novel regularization technique for deep neural networks to enhance generalization. Inspired by the human ability to capture concise and abstract patterns, we hypothesize that generalizable correlations are expected to be easier to imitate. LoT operationalizes this concept to improve the generalization of the main model with auxiliary student learners. The student learners are trained by the main model and, in turn, provide feedback to help the main model capture more generalizable and imitable correlations. Our experimental results across several domains, including Computer Vision, Natural Language Processing, and methodologies like Reinforcement Learning, demonstrate that the introduction of LoT brings significant benefits compared to training models on the original dataset. The results suggest the effectiveness and efficiency of LoT in identifying generalizable information at the right scales while discarding spurious data correlations, thus making LoT a valuable addition to current machine learning. Code is available at https://github.com/jincan333/LoT.

cs.LG↗

arXiv2023

EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision

We present EmerNeRF, a simple yet powerful approach for learning spatial-temporal representations of dynamic driving scenes. Grounded in neural fields, EmerNeRF simultaneously captures scene geometry, appearance, motion, and semantics via self-bootstrapping. EmerNeRF hinges upon two core components: First, it stratifies scenes into static and dynamic fields. This decomposition emerges purely from self-supervision, enabling our model to learn from general, in-the-wild data sources. Second, EmerNeRF parameterizes an induced flow field from the dynamic field and uses this flow field to further aggregate multi-frame features, amplifying the rendering precision of dynamic objects. Coupling these three fields (static, dynamic, and flow) enables EmerNeRF to represent highly-dynamic scenes self-sufficiently, without relying on ground truth object annotations or pre-trained models for dynamic object segmentation or optical flow estimation. Our method achieves state-of-the-art performance in sensor simulation, significantly outperforming previous methods when reconstructing static (+2.93 PSNR) and dynamic (+3.70 PSNR) scenes. In addition, to bolster EmerNeRF's semantic generalization, we lift 2D visual foundation model features into 4D space-time and address a general positional bias in modern Transformers, significantly boosting 3D perception performance (e.g., 37.50% relative improvement in occupancy prediction accuracy on average). Finally, we construct a diverse and challenging 120-sequence dataset to benchmark neural fields under extreme and highly-dynamic settings.

cs.CV↗