Search: “inference-time-scaling”

Smart search ranks by meaning as well as keywords (one row per story, last 45 days).

Architecting memory and storage in the AI era

Analysis argues AI inference shifts data-center bottlenecks to memory and storage, urging balanced compute, memory, storage, and network architecture over raw compute.

MIT Technology Review, citing Tirias Research principal analyst Jim McGregor, argues that AI inference and agentic workloads make data movement the key constraint, elevating memory and storage from background hardware to strategic assets. The piece says RAG and real-time inference require continuous data retrieval and caching that legacy infrastructure cannot support. It frames infrastructure planning as a business decision balancing performance, efficiency, cost, and scalability in healthcare, finance, and customer-facing AI.

MIT Technology Review · AI·Sep 4, 18:39 UTC · 12d agoAI industry

14

How Model Growth, Recursion, and Boundary Operators Influence Scaling Exponents

Researchers show model growth via looped transformers improves scaling exponents; a 7.4B architecture matches GPT-3 13B with roughly 20x less compute.

The paper shows that architectural interventions, contrary to conventional wisdom, can modify pre-training scaling exponents and yield exponential performance gains with compute. Looped transformers with increasing loop counts provide a model growth mechanism; a 7.4B model-growth architecture matches GPT-3 13B on CORE with roughly 20x less compute, with efficiency gains that increase with scale. A boundary operator that normalizes and injects an earlier block also improves compute efficiency, and in data-constrained multi-epoch settings increasing loops with scale is compute-optimal.

arXiv cs.AI / cs.LG / cs.CL·Sep 16, 17:36 UTC · 11h agoAI research

42

Likelihood-free inference with nuisance parameters through normalizing flows

Researchers decompose normalizing flows to derive near-pivotal statistics for likelihood-free inference with nuisance parameters, recovering the t-test and beating Welch limits.

A new paper decomposes neural-network normalizing flows to uncover pivotal statistics in the presence of nuisance parameters using only a sample generator from the distribution of interest. The statistic is near-pivotal in the sense of minimum average KL-divergence of its p-values and can incorporate prior knowledge of group invariances such as translation and scale. Experiments show it recovers the one-sample t-test almost exactly, outperforms the Welch test on worst-case size over a constrained variance-ratio range, and delivers higher power and much faster runtime than profile likelihood-ratio techniques on small-to-moderate samples.

arXiv cs.AI / cs.LG / cs.CL·Sep 9, 17:58 UTC · 7d agoAI research

16

When Does Scale-Invariant Optimization Become Unstable? An Exact Schedule Law with Weight Decay

Researchers derive an exact law linking learning-rate schedules and weight decay in normalized networks, pinpointing when scale-invariant optimization destabilizes.

The paper shows that normalization makes large parts of neural networks scale-invariant, creating a hidden feedback loop where learning-rate schedules and weight decay interact through the parameter norm to control the effective optimizer step. An exact discrete-time law with a single scalar quantity separates contraction- and expansion-dominated effective learning-rate regimes, and the balance point is intrinsically unstable, so constant learning rate with weight decay produces recurrent behavior instead of a stable equilibrium. A unified homogeneous-optimizer framework explains why adaptive methods stabilize more weakly under normalization. The law is validated with high precision on MLPs, CNNs, and GPT-2 across MNIST, CIFAR, WikiText, and OpenWebText, with code released on GitHub.

arXiv cs.AI / cs.LG / cs.CL·Sep 8, 17:46 UTC · 8d agoAI research

30

OracleZoom: On-Policy Self-Distillation Inspired Reference-Constrained Recursive Image Super Resolution

OracleZoom enables recursive extreme-scale image super-resolution via reference-constrained on-policy distillation, reducing hallucinations at deep zoom scales.

OracleZoom tackles recursive super-resolution, where repeated feeding of predictions back into the same model leaves deeper-scale outputs unsupervised as required source resolution grows geometrically. The framework trains on its own trajectory while carrying the last ground-truth evidence beyond the supervision boundary, combining direct and cross-scale supervision, a no-reference quality objective, a KL-constrained pretrained latent prior, and EMA consistency. Across seven datasets it achieves state-of-the-art SR quality across zoom scales, averaging 0.713 CLIPIQA with larger gains at deeper scales and significantly reduced hallucinations. Code, data, and models are publicly released.

Hugging Face daily papers·Sep 5, 20:00 UTC · 11d agoAI research

20

Bridging the Confidence Gap: Temperature Scaling for Calibrating Test-Time Prompt Tuning

CoTS temperature scaling cuts test-time prompt tuning's expected calibration error from 11.90% to 5.38% on ImageNet variants while raising accuracy.

The paper proposes CoTS, a post-hoc calibration method that applies temperature scaling to minimize the confidence gap between test-time-adapted and zero-shot predictions. A weak-strong ensemble variant, E-CoTS, further exploits multiple test-time augmentations to boost accuracy while maintaining calibration. E-CoTS reduces average expected calibration error from 11.90% to 5.38% on ImageNet variants while increasing accuracy from 60.74% to 62.95%.

arXiv cs.AI / cs.LG / cs.CL·Sep 15, 16:25 UTC · 1d agoAI research

20

Large Language Models Develop Belief State Geometry In-Context

Probing six open-source LLMs on HMM-generated data shows belief states are linearly decodable (R² 0.83–0.99), suggesting in-context learning approximates Bayesian prediction.

Researchers prompted six open-source LLMs with data from 40 hidden Markov models selected for non-trivial belief structure and probed residual-stream activations for belief states (posteriors over hidden states). Belief states were linearly decodable with peak R² values of 0.83–0.99 across HMM/LLM combinations, spanning early to late layers. Patching and steering the probe-identified subspace preserved downstream prediction quality while control interventions degraded performance substantially, establishing functional relevance. The results provide representation-level evidence that in-context learning approximates optimal Bayesian prediction over a context-inferred generative model.

arXiv cs.AI / cs.LG / cs.CL·Sep 15, 16:17 UTC · 1d agoAI research1

45

DynSHAP: Towards Explainable Dynamic Survival Analysis

DynSHAP extends SHAP explainability to dynamic survival analysis, treating time-feature pairs as Shapley players for longitudinal clinical predictions.

DynSHAP adapts marginal SHAP estimators to dynamic survival analysis by treating time-feature pairs as players in the Shapley game, handling longitudinal irregular inputs and functional survival outputs. Temporal DynSHAP learns linear feature dependencies over time and addresses them with conditional sampling. On synthetic data with ground-truth attributions it recovers temporally dependent features more accurately than marginal estimators, and it produces faithful attributions on two real-world clinical datasets across two DSA architectures.

arXiv cs.AI / cs.LG / cs.CL·Sep 11, 16:39 UTC · 5d agoAI research

22

BeaconKV: Key-Value Cache Compression Guided by Beacon Queries for Efficient Large Reasoning Model Inference

BeaconKV introduces training-free KV cache compression using beacon queries, cutting long-reasoning inference memory up to 5.8x while preserving accuracy.

The paper shows recency-based KV cache compression assumptions fail in long-horizon reasoning because Thought Revisiting Tokens (TRT) re-attend to distant context such as early task-solving plans. TRT queries cluster into a small number of similarity groups, which BeaconKV exploits by maintaining compact beacon query representatives to anticipate revisited KV pairs without storing full query history. The training-free method achieves up to 5.8x memory reduction and over 4.3x throughput improvement across four open-source large reasoning models while nearly preserving full cache accuracy.

Hugging Face daily papers·Sep 3, 20:00 UTC · 13d agoAI research1

33

Why Is Video Still So Expensive? A Survey of Inference-Efficiency Mechanisms in Video and Audiovisual LLMs

A survey catalogs inference-efficiency techniques for video and audiovisual LLMs, mapping bottlenecks in sampling, encoding, token reduction, and LLM decoding.

This survey covers inference-efficiency mechanisms for visual and audiovisual video LLMs, reporting reductions in parameters, FLOPs, latency, memory, and token counts. It organizes methods by pipeline stage, covering frame sampling, modality encoding, connector-level token reduction, and LLM prefilling and decoding for systems built since late 2022. The authors compile accuracy-cost comparisons under shared host models and input protocols, identify gaps in audiovisual efficiency and standardized evaluation, and maintain a public repository.

Hugging Face daily papers·Sep 8, 20:00 UTC · 8d agoAI research

40

A*-Thought-V2: Efficient Latent Reasoning via Geometric Dynamics of LLM

A*-Thought-V2 compresses redundant chain-of-thought steps into latent tokens guided by hidden-state geometry, improving accuracy up to 2.6% while halving response length.

A*-Thought-V2 models chain-of-thought as a hidden-state trajectory projected into a 3D PCA space and compresses steps whose transitions deviate from the question-to-solution direction into continuous latent tokens, keeping aligned steps explicit. Training uses stepwise embedding forcing and label forcing with soft multi-modal vocabulary supervision. On Qwen3.5-9B and Qwen3.6-27B across six in-domain and out-of-domain benchmarks it improves average accuracy by up to 2.6%, cuts response length by up to half, and raises Accuracy per Computation Unit 2.29x while reducing preprocessing and training time by 94.6% and up to 80.3%.

arXiv cs.AI / cs.LG / cs.CL·Sep 7, 17:56 UTC · 9d agoAI research

36

rMuscle: Robotic Muscle Memory for Efficient Vision-Language-Action Model Inference

rMuscle, a caching-based inference framework for vision-language-action models, achieves 1.29-1.42x speedups on RTX 4090 and Jetson Thor while preserving success rates.

rMuscle is a real-time inference framework for Vision-Language-Action (VLA) models that exploits cross-execution similarity in repetitive robot tasks via a dual-phase muscle-memory cache. The Context Cache reuses visual-token outputs to reduce computation, while the Action Cache reuses neuron activation patterns to reduce weight accesses, with online recomputation and sliding-window retrieval keeping overhead low. It achieves 1.29-1.42x speedups on RTX 4090 and Jetson Thor across LIBERO, RoboTwin, and real-world manipulation tasks while maintaining original success rates.

arXiv cs.AI / cs.LG / cs.CL·Sep 16, 17:34 UTC · 11h agoAI tools & infra

32

harshatheg/Qwen-2.5-1B-RLCD — new model trending #30 on Hugging Facenew

A community MLX inference engine evaluates constrained JSON schema fields in parallel on Apple Silicon, reporting 5.6-7.0x latency speedups with guaranteed schema validity.

The repository harshatheg/Qwen-2.5-1B-RLCD appeared at #30 on Hugging Face trending, but its content describes Parallel Constrained Decoding, an MLX-based inference engine for structured extraction and classification on Apple Silicon Macs. Benchmarked with mlx-community/Qwen2.5-1.5B-Instruct-4bit on an M4 Max, it reports 5.6x-7.0x latency reductions (e.g., 1,900 ms to 270 ms for a 28-field support triage task) with 100% syntactic validity and calibrated field-level probabilities. The engine prefills a single KV-cache, broadcasts it across all schema fields, and slices logits to valid candidate tokens for enum fields with up to 255 choices.

Hugging Face trending models·Sep 16, 01:35 UTC · 1d agoAI tools & infra

15

When Agents Slow Down: Understanding LLM Agents' Test-Time Strategies via Elo-per-token Analysis

Elo-per-token analysis shows LLM agents' marginal gains drop below independent sampling at scale; parallel sessions beat one long session.

The paper proposes Elo-per-token analysis, using a Bradley-Terry model to measure how agent performance scales with token budget on open-ended tasks with continuous scoring. Across four agents and four benchmarks with sessions up to 100M tokens, agents initially convert tokens to Elo faster than independent sampling but eventually slow below the linear-in-log-compute reference. The authors define a scaling inflection point and show that splitting 100M tokens across parallel sessions on FrontierCS Polyomino Packing gains +264 Elo over one long session and +355 over ten short sessions. Human contestants on shared AtCoder Heuristic Contest tasks improve superlinearly, indicating headroom over current agents.

Hugging Face daily papers·Sep 13, 20:00 UTC · 3d agoAI research4· 2 reads

48

Evaluating Time-Series Foundation Models and Multimodal Dietary Context for CGM Forecasting

Study finds zero-shot time-series foundation models underperform on CGM forecasting; fine-tuned Chronos-Bolt cuts RMSE up to 18.4% and dietary context adds signal.

The paper evaluates time-series foundation models for continuous glucose monitoring forecasting across eight public datasets covering Type 1 diabetes, Type 2 diabetes, and non-diabetes populations. Under a unified protocol, zero-shot foundation models did not consistently outperform baselines like Elastic Net and PatchTST, but lightweight fine-tuning did, with fine-tuned Chronos-Bolt reducing RMSE by 6.5%-18.4% in the T1D cohort and 8.6%-18.2% in the non-diabetes/T2D cohort. A residual-based fusion framework adding dietary context from CGMacros reduced overall RMSE by about 3% and postprandial RMSE by about 15% versus CGM-only baselines.

arXiv cs.AI / cs.LG / cs.CL·Sep 10, 17:43 UTC · 6d agoAI research

28

A*-Thought-V2: Efficient Latent Reasoning via Geometric Dynamics of LLM

A*-Thought-V2 compresses chain-of-thought into latent tokens using geometric hidden-state dynamics, cutting computation while improving accuracy on Qwen models.

A*-Thought-V2 models chain-of-thought as a hidden-state trajectory and interleaves explicit text with continuous latent tokens, compressing steps whose transitions deviate from the question-to-solution direction. Trained via stepwise embedding forcing and label forcing with soft multi-modal supervision, it was evaluated on Qwen3.5-9B and Qwen3.6-27B across six benchmarks. Reported results include up to 2.6% average accuracy gain, up to 50% shorter responses, 2.29x higher Accuracy per Computation Unit, 94.6% faster preprocessing, and up to 80.3% faster training.

Hugging Face daily papers·Sep 7, 13:56 UTC · 9d agoAI research

48

Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-Training

NVIDIA researchers detail an end-to-end system for online draft co-training that speeds speculative decoding in large-scale long-context RL post-training.

The paper tackles scaling online draft co-training for speculative decoding in RL post-training, where rollout generation dominates cost. It extends packed, load-balanced zigzag ring attention to merge rank-local branch attention with causal main-sequence attention for context parallelism, and introduces TapChannel to transport target features across pipeline-parallel stages without changing the schedule. Experiments show co-trained drafts tracking the policy baseline with substantial rollout and end-to-end speedups up to 122B parameters and strong scaling at 256K tokens.

Hugging Face daily papers·Sep 6, 20:00 UTC · 10d agoAI research

26

Exponential Hardness of Off-Policy Evaluation under History-Dependent Logging

Researchers prove off-policy evaluation under history-dependent logging requires exponentially many episodes, resolving a hardness question for model-based POMDP evaluation.

The paper constructs POMDPs with at most two latent states per stage, three actions, and a three-memory-state logger where evaluating a known deterministic target policy to accuracy 1/8 requires Θ((3/2)^H log(1/δ)) episodes for any horizon H≥3. Coverage and outcome-revealing conditions hold with constants independent of H, yet a reset erases the unknown transition that determines the target value. The authors characterize the resulting statistical experiment exactly, derive a matching optimal estimator, and validate predictions on a two-lane gridworld. This settles the history-dependent-logging, model-based case posed by Zhang and Jiang (arXiv:2503.01134).

arXiv cs.AI / cs.LG / cs.CL·Sep 16, 17:56 UTC · 10h agoAI research

20

PARSER: Read in Parallel, Reason in Depth for Long-Context LLM Agents

PARSER uses parallel reader subagents and an RL-trained lead agent for long-context QA, beating baselines and cutting latency up to 11x.

The PARSER paper decouples reading from reasoning: frozen subagents each read one document chunk in parallel while an RL-optimized lead agent iteratively broadcasts queries and aggregates evidence in scatter-gather rounds. On multi-hop QA with 7K to 896K token contexts, a 4B-backbone PARSER beats the strongest sequential memory baseline by 5.7 points on average and 12.0 points at 896K tokens, and a 9B version surpasses DeepSeek-V4-Pro by 6.3 points. Controlled experiments show robustness to evidence position, order, and distance perturbations, with inference latency reduced by up to 11x.

Hugging Face daily papers·Sep 5, 20:00 UTC · 11d agoAI research1

52

Convergent Emergence of In-Context Learning Across Modalities

Controlled experiments show few-shot in-context learning emerges across six modalities including language, genomes, images, and proteins, partially supporting a convergence hypothesis.

The paper tests the Convergent Emergence Hypothesis: that few-shot in-context learning, when it emerges, shares a common cross-modality difficulty profile. A controlled framework instantiated the same task suite across six modalities: language, genome, integer sequences, time series, images, and proteins. Paired-mapping ICL emerged in all six modalities, surpassed controlled baselines, and showed correlated per-task effects in five of them, providing partial support for the hypothesis.

Hugging Face daily papers·Sep 11, 20:00 UTC · 5d agoAI research

30

Drift-Constrained Optimization: Only Direction Matters in Fine-Tuning Instruct Models

Drift-Constrained Optimization reformulates fine-tuning as update-direction selection, letting Qwen3 models improve target tasks within a behavioral drift budget.

The paper specifies a behavioral drift budget before optimization and shows that update direction is the remaining degree of freedom, reformulating fine-tuning as a direction-selection problem. In a stringent QA-only setting where instruct models must still generate multi-step reasoning at inference, a coarse layer-selective probe reverses the failure of QA-only fine-tuning. Across Qwen3-8B and Qwen3-14B, these directions substantially improve scientific reasoning and multilingual translation, matching or outperforming dedicated translation systems over 100+ languages and giving stronger initialization for reinforcement learning.

Hugging Face daily papers·Sep 11, 20:00 UTC · 5d agoAI research

48

RetroThinker: Enabling Retrospective Thinking in Speech LLMs

RetroThinker is a post-training framework letting the Moshi speech LLM self-correct reasoning mid-stream, adding 11% GSM8K accuracy at similar latency.

Researchers introduce RetroThinker, a multi-stage post-training framework that equips the Moshi speech LLM to verify and forward-correct chain-of-thought steps during streaming inference. It combines supervised fine-tuning on curated retrospective thinking data with length-based direct preference optimization (DPO). On GSM8K it achieves an 11% absolute accuracy gain over non-retrospective baselines at comparable latency.

arXiv cs.AI / cs.LG / cs.CL·Sep 10, 17:41 UTC · 6d agoAI research1

28

Continual Learning Mechanisms Compose for Long-Horizon Memorization

Composing data, function, and weight anchors with merged LoRA raises 100-task long-horizon retention from 1.2% to 34.9% in continual fine-tuning.

The paper introduces long-horizon memorization: a model learns 100 query-answer tasks through continual supervised fine-tuning without retaining earlier examples or receiving task identifiers at inference. No single continual learning mechanism maintains strong retention at this horizon, so the authors compose complementary mechanisms along data/function/weight anchors and low-rank allocation rules. The best method combining all three anchors with merged LoRA ranks among the top 3 methods on all three datasets and raises average final retention from 1.2% to 34.9%, a 28-fold improvement.

Hugging Face daily papers·Sep 6, 20:00 UTC · 10d agoAI research

42

LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence

LimiX-2 scales Contextual Mechanism Networks pretrained via context-conditional masked modeling, beating tabular foundation models on TabArena, TALENT, and BCCO benchmarks.

LimiX-2 is a new tabular model in the LimiX family, developed through model and data scaling guided by previously established scaling laws under the Contextual Mechanism Networks (CMNs) paradigm. It is pretrained with Context-Conditional Masked Modeling (CCMM) on synthetic datasets generated by structural causal models spanning diverse graph structures, functional mechanisms, and observation processes. It outperforms dataset-specific models and tabular foundation models on TabArena, TALENT, and BCCO, and its feature attention encodes direct causal relationships, enabling accurate causal skeleton recovery.

arXiv cs.AI / cs.LG / cs.CL·Sep 15, 17:30 UTC · 1d agoAI research 2 sources1

18

[AINews] Fal’s H3 Max Live breaks the infinite videogen barrier

Fal post-trained MiniMax H3 into a 'Max' variant with 35x-faster inference, enabling faster-than-realtime AI video generation and infinite streams.

Fal post-trained MiniMax's H3 model into a 'Max' variant and optimized it for its in-house inference engine, achieving roughly 35x the speed of the official endpoint. The optimization enables faster-than-realtime video generation, demonstrated by an infinite interactive AI-generated stream productized by levels.io. The roundup also notes Meta Muse Code's general availability with an SDK, open DeepSeek-V4-Flash-Vision-Exp weights, GLM-5.3-Flash's strong agentic cost/performance rankings, and Tencent's 770B-parameter Hy4 Preview MoE with 49B active parameters.

Latent Space·Sep 1, 04:36 UTC · 16d agoAI industry

50

Beyond Training: A Feasibility Taxonomy for Inference-Time AI Governance

A study maps twenty inference-time AI governance mechanisms, finding commercial readiness only against cooperative deployers and no adequate defense versus state-level adversaries.

The paper develops a feasibility taxonomy of twenty inference-time AI governance mechanisms across monitoring, verification, and enforcement, each rated on a four-point readiness scale against a four-vendor evidence base. Fifteen of the twenty mechanisms have commercial technical substrates in production today, though governance-grade assurance and adversarial robustness vary substantially. Stress testing shows readiness holds only against a cooperative deployer and low-to-medium-capability user: no mechanism rates adequate against a high-capability state-level deployer, and fine-tuning removes model-internal enforcement components. A second-rater reliability check on readiness ratings returned a quadratic-weighted Cohen's kappa of 0.74.

arXiv cs.CR·Sep 9, 12:37 UTC · 7d agoAI policy

28

Double descent is the principle of least action

A statistical mechanics analysis explains double descent: finite-time diffusion induces effective weight decay that regularizes models as parameters grow.

The paper models stochastic gradient-based training as a particle diffusing over the training-loss energy landscape at an induced temperature, sampling parameters via a Boltzmann distribution. Finite training time carries an effective weight decay, making every parameter a quadratic degree of freedom governed by the equipartition theorem. Adding parameters at fixed training loss lowers the temperature and the L2 norm of the stationary path, increasing effective regularization and explaining the double descent phenomenon.

arXiv cs.AI / cs.LG / cs.CL·Sep 16, 17:17 UTC · 11h agoAI research

20

Bridging Control, Inference, Transport, and Thermodynamics: From Theory to Applications in Learning

Review connects control theory, optimal transport, probabilistic inference, thermodynamics, and machine learning via free-energy optimization under constraints.

The review unifies five fields: control theory, optimal transport, probabilistic inference, non-equilibrium thermodynamics, and machine learning. The common conceptual thread is optimization of free-energy-like functionals under dynamical or statistical constraints. Selected applications are presented in reinforcement learning, variational inference, and generative modeling. The tutorial-style text assumes no prior familiarity and begins from physics principles.

arXiv cs.AI / cs.LG / cs.CL·Sep 14, 17:16 UTC · 2d agoAI research

15

Scaling Automatic Research Agents via World Models

WMRL replaces environment execution with a world model in RL, accelerating research-agent post-training 3-4x and letting 4B/9B agents beat 48B/120B open-weight agents.

The paper identifies that environment execution dominates RL training cost for automatic research agents because each execution occupies an exclusive sandbox while generation batches efficiently. World Model RL (WMRL) substitutes a learned world model for execution, with Online Debiasing and Inverse-Variance Denoising to handle reward bias and noise, and the paper proves both improve convergence guarantees. WMRL accelerates training 3-4x across tasks and outperforms standard RL baselines; post-trained 4B and 9B agents beat 48B and 120B open-weight agents on held-out benchmarks. WMRL also transfers to post-training embodied VLA policies.

Hugging Face daily papers·Aug 28, 20:00 UTC · 19d agoAI research1

45

Attention Quantization for Tabular Foundation Models

FP8 quantization of attention queries, keys, and values speeds tabular foundation model inference up to 1.7x with no accuracy loss.

The paper develops an FP8 quantization strategy targeting attention calculations (queries, keys, values) in tabular foundation models, arguing attention matters more than weight or KV cache quantization given their differing size and serving patterns versus LLMs. Aligning quantization error between test rows and training rows proves crucial, since misalignment causes drastic accuracy drops. A Triton kernel using explicit FP8 matrix multiplication achieves up to 1.7x speedup over regular 16-bit kernels, with no relevant accuracy loss on TabPFN-v3 and TabICLv2 across TabArena and BeyondArena benchmarks.

arXiv cs.AI / cs.LG / cs.CL·Sep 11, 16:31 UTC · 5d agoAI research1

28